### Set yourself up for promotion or get a better job by Acing the AWS Certified Data Engineer Associate Exam (DEA-C01) with the eBook or App below (Data and AI)

Download the Ace AWS DEA-C01 Exam App:

iOS - Android

**Machine Learning Engineer Interview Questions and Answers**

**Learning: Supervised, Unsupervised, Reinforcement Learning**

**What is Machine Learning?**

Machine learning is the study of computer algorithms that improve automatically through experience. It is seen as a subset of artificial intelligence. Machine Learning explores the study and construction of algorithms that can learn from and make predictions on data. You select a model to train and then manually perform feature extraction. Used to devise complex models and algorithms that lend themselves to a prediction which in commercial use is known as predictive analytics.

**Below are the most common Machine Learning use cases and capabilities:**

Machine Learning For Dummies App

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**#MachineLearning #AI #ArtificialIntelligence #ML #MachineLearningForDummies #MLOPS #NLP #ComputerVision #AWSMachineLEarning #AzureAI #GCPML**

**What is Supervised Learning? **

Supervised learning is the machine learning task of** inferring a function from labeled training data.** The training data consist of a set of training examples.

**Algorithms:** Support Vector Machines, Regression, Naive Bayes, Decision Trees, K-nearest Neighbor Algorithm and Neural Networks

**Example:** If you built a fruit classifier, the labels will be “this is an orange, this is an apple and this is a banana”, based on showing the classifier examples of apples, oranges and bananas.

**What is Unsupervised learning?**

Unsupervised learning is a type of machine learning algorithm used to **draw inferences from datasets consisting of input data without labelled responses.**

**Algorithms:** Clustering, Anomaly Detection, Neural Networks and Latent Variable Models

**Example:** In the same example, a fruit clustering will categorize as “fruits with soft skin and lots of dimples”, “fruits with shiny hard skin” and “elongated yellow fruits”.

### Advertise with us - Post Your Good Content Here

We are ranked in the Top 20 on Google

### AI Dashboard is available on the Web, Apple, Google, and Microsoft, PRO version

**Explain the difference between supervised and unsupervised machine learning?**

In supervised machine learning algorithms, we have to provide labeled data, for example, prediction of stock market prices, whereas in unsupervised we need not have labeled data, for example, classification of emails into spam and non-spam.

**What is deep learning, and how does it contrast with other machine learning algorithms?**

Deep learning is a subset of machine learning that is concerned with neural networks: how to use backpropagation and certain principles from neuroscience to more accurately model large sets of unlabelled or semi-structured data. In that sense, deep learning represents an unsupervised learning algorithm that learns representations of data through the use of neural nets.

**What is Problem Formulation in Machine Learning?**

The problem formulation phase of the ML Pipeline is critical, and it’s where everything begins. Typically, this phase is kicked off with a question of some kind. Examples of these kinds of questions include: Could cars really drive themselves? What additional product should we offer someone as they checkout? How much storage will clients need from a data center at a given time?

The problem formulation phase starts by seeing a problem and thinking “what question, if I could answer it, would provide the most value to my business?” If I knew the next product a customer was going to buy, is that most valuable? If I knew what was going to be popular over the holidays, is that most valuable? If I better understood who my customers are, is that most valuable?

However, some problems are not so obvious. When sales drop, new competitors emerge, or there’s a big change to a company/team/org, it can be easy to say, “I see the problem!” But sometimes the problem isn’t so clear. Consider self-driving cars. How many people think to themselves, “driving cars is a huge problem”? Probably not many. In fact, there isn’t a problem in the traditional sense of the word but there is an opportunity. Creating self-driving cars is a huge opportunity. That doesn’t mean there isn’t a problem or challenge connected to that opportunity. How do you design a self-driving system? What data would you look at to inform the decisions you make? Will people purchase self-driving cars?

Part of the problem formulation phase includes seeing where there are opportunities to use machine learning.

To formulate a problem in ML, consider the following questions:

- Is machine learning appropriate for this problem, and why or why not?
- What is the ML problem if there is one, and what would a success metric look like?
- What kind of ML problem is this?
- Is the data appropriate?

**Machine Learning Problem Formulation Examples:**

1) Amazon recently began advertising to its customers when they visit the company website. The Director in charge of the initiative wants the advertisements to be as tailored to the customer as possible. You will have access to all the data from the retail webpage, as well as all the customer data.

**ML is appropriate because of the scale, variety and speed required**. There are potentially thousands of ads and millions of customers that need to be served customized ads immediately as they arrive to the site.- The problem is ads that are not useful to customers are a wasted opportunity and a nuisance to customers, yet not serving ads at all is a wasted opportunity. So how does Amazon serve the most relevant advertisements to its retail customers?
**Success would be the purchase of a product that was advertised.**

- This is a
**supervised learning problem**because we have**a labeled data point**, our success metric, which is the purchase of a product. - This
**data is appropriate**because it is both the retail webpage data as well as the customer data.

**What are the different Algorithm techniques in Machine Learning?**

The different types of techniques in Machine Learning are

● Supervised Learning

● Unsupervised Learning

● Semi-supervised Learning

● Reinforcement Learning

● Transduction

● Learning to Learn

Machine Learning For Dummies App

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**#MachineLearning #AI #ArtificialIntelligence #ML #MachineLearningForDummies #MLOPS #NLP #ComputerVision #AWSMachineLEarning #AzureAI #GCPML**

**What’s the difference between a generative and discriminative model?**

A generative model will learn categories of data while a discriminative model will simply learn the distinction between different categories of data. Discriminative models will generally outperform generative models on classification tasks.

**What Are the Applications of Supervised Machine Learning in Modern Businesses?**

Applications of supervised machine learning include:

● **Email Spam Detection**

Here we train the model using historical data that consists of emails categorized as spam or not spam. This labeled information is fed as input to the model.

● **Healthcare Diagnosis**

By providing images regarding a disease, a model can be trained to detect if a person is suffering from the disease or not.

● **Sentiment Analysis**

This refers to the process of using algorithms to mine documents and determine whether they’re positive, neutral, or negative in sentiment.

● **Fraud Detection**

Training the model to identify suspicious patterns, we can detect instances of possible fraud.

**What Is Semi-supervised Machine Learning?**

Supervised learning uses data that is completely labeled, whereas unsupervised learning uses no training data.

In the case of semi-supervised learning, the training data contains a small amount of labeled data and a large amount of unlabeled data.

**What Are Unsupervised Machine Learning Techniques?**

There are two techniques used in unsupervised learning: clustering and association.

**Clustering**

● Clustering problems involve data to be divided into subsets. These subsets, also called clusters, contain data that are similar to each other. Different clusters reveal different details about the objects, unlike classification or regression.

**Association**

● In an association problem, we identify patterns of associations between different variables or items.

● For example, an eCommerce website can suggest other items for you to buy, based on the prior purchases that you have made, spending habits, items in your wish list, other customers’ purchase habits, and so on.

**What evaluation approaches would you work to gauge the effectiveness of a machine learning model?**

You would first split the dataset into training and test sets, or perhaps use cross-validation techniques to further segment the dataset into composite sets of training and test sets within the data. You should then implement a choice selection of performance metrics: here is a fairly comprehensive list. You could use measures such as the F1 score, the accuracy, and the confusion matrix. What’s important here is to demonstrate that you understand the nuances of how a model is measured and how to choose the right performance measures for the right situations.

**What Are the Three Stages of Building a Model in Machine Learning?**

The three stages of building a machine learning model are:

● Model Building Choose a suitable algorithm for the model and train it according to the requirement

● Model Testing Check the accuracy of the model through the test data

● Applying the Mode Make the required changes after testing and use the final model for real-time projects. Here, it’s important to remember that once in a while, the model needs to be checked to make sure it’s working correctly. It should be modified to make sure that it is up-to-date.

**A data scientist wants to visualize the correlation between features in their dataset. What tool(s) can they use to visualize this in a correlation matrix? **

Answer: **Matplotlib, Seaborn**

**You are preprocessing a dataset that includes categorical features. You want to determine which categories of particular features are most common in your dataset. Which basic descriptive statistic could you use?**

Answer: **Mode**

**What are some examples of categorical features?**

In machine learning and data science, **categorical features are variables that can take on one of a limited number of values**. For example, a categorical feature might represent the color of a car as Red, Yellow, or Blue. In general, categorical features are used to represent discrete characteristics (such as gender, race, or profession) that can be sorted into categories. When working with categorical features, it is often necessary to convert them into numerical form so that they can be used by machine learning algorithms. This process is known as encoding, and there are several different ways to encode categorical features. One common approach is to use a technique called one-hot encoding, which creates a new column for each possible category. For example, if there are three colors **(Red, Yellow, and Blue)**, then each color would be represented by a separate column where all the values are either 0 or 1 (1 indicates that the row belongs to that category). Machine learning algorithms can then treat each column as a separate feature when training the model. Other approaches to encoding categorical data include label encoding and target encoding. These methods are often used in conjunction with one-hot encoding to improve the accuracy of machine learning models.

**How many variables are enough for multiple regressions?**

**Which of the following is most suitable for supervised learning?**

**Identifying birds in an image**

**You’ve plotted the correlation matrix of your dataset’s features and realized that two of the features present a high negative correlation (-0.95). What should you do?**

Answer: **Remove one of the features**

**You are in charge of preprocessing the data your publishing company wants to use for a new ML model they’re building, which aims to predict the influence an academic journal will have in its field. The preprocessing step is necessary to prepare the data for model training. What type of issue with the data might you encounter during this preprocessing phase? **

Answer: **Outliers, Missing values**

**A Machine Learning Engineer is creating and preparing data for a linear regression model. However, while preparing the data, the Engineer notices that about 20% of the numerical data contains missing values in the same two columns. The shape of the data is 500 rows by 4 columns, including the target column.**

**How can the Engineer handle the missing values in the data?**

Answer:** Fill he missing values with mean of the column, Impute the missing values using regression**

**A Data Scientist created a correlation matrix between nine variables and the target variable. The correlation coefficient between two of the numerical variables, variable 1 and variable 5, is -0.95. How should the Data Scientist interpret the correlation coefficient?**

Answer: **As variable 1 increases, variable 5 decreases**

**An advertising and analytics company uses machine learning to predict user response to online advertisements using a custom XGBoost model. The company wants to improve its ML pipeline by porting its training and inference code, written in R, to Amazon SageMaker, and do so with minimal changes to the existing code.**

Answer: **Use the Build Your Own Container (BYOC) Amazon Sagemaker option.****Create a new docker container with the existing code. Register the container in Amazon Elastic Container registry. with the existing code. Register the container in Amazon Elastic Container Registry. Finally run the training and inference jobs using this container.**

**An ML engineer at a text analytics startup wants to develop a text classification model. The engineer collected large amounts of data to develop a supervised text classification model. The engineer is getting 99% accuracy on the dataset but when the model is deployed to production, it performs significantly worse. What is the most likely cause of this?**

Answer: The engineer did not split the data to validate the model on unseen data.

For a classification problem, what does the loss function measure?

Answer: A loss function measures how accurate your prediction is with respect to the true values.

**Gradient Descent is an important optimization method. What are 3 TRUE statements about the gradient descent method?**

Answer: **It tries to find the minimum of a loss function. It can involve multiple iterations****It uses learning rate to multiply the effect of gradients**

**What is Deep Learning?**

Deep Learning is nothing but a paradigm of machine learning which has shown incredible promise in recent years. This is because of the fact that Deep Learning shows a great analogy with the functioning of the neurons in the human brain.

Machine Learning For Dummies App

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**#MachineLearning #AI #ArtificialIntelligence #ML #MachineLearningForDummies #MLOPS #NLP #ComputerVision #AWSMachineLEarning #AzureAI #GCPML**

**What is the difference between machine learning and deep learning?**

Machine learning is a field of computer science that gives computers the ability to learn without being explicitly programmed. Machine learning can be categorized in the following four categories.

1. Supervised machine learning,

2. Semi-supervised machine learning,

3. Unsupervised machine learning,

4. Reinforcement learning.

Deep Learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks.

• The main difference between deep learning and machine learning is due to the way data is

presented in the system. Machine learning algorithms almost always require structured data, while deep learning networks rely on layers of ANN (artificial neural networks).

• Machine learning algorithms are designed to “learn” to act by understanding labeled data and then use it to produce new results with more datasets. However, when the result is incorrect, there is a need to “teach them”. Because machine learning algorithms require bulleted data, they are not suitable for solving complex queries that involve a huge amount of data.

• Deep learning networks do not require human intervention, as multilevel layers in neural

networks place data in a hierarchy of different concepts, which ultimately learn from their own mistakes. However, even they can be wrong if the data quality is not good enough.

• Data decides everything. It is the quality of the data that ultimately determines the quality of the result.

• Both of these subsets of AI are somehow connected to data, which makes it possible to represent a certain form of “intelligence.” However, you should be aware that deep learning requires much more data than a traditional machine learning algorithm. The reason for this is that deep learning networks can identify different elements in neural network layers only when more than a million data points interact. Machine learning algorithms, on the other hand, are capable of learning by pre-programmed criteria.

**Can you explain the differences between supervised, unsupervised, and reinforcement learning?**

In supervised learning, we train a model to learn the relationship between input data and output

data. We need to have labeled data to be able to do supervised learning.

With unsupervised learning, we only have unlabeled data. The model learns a representation of the data. Unsupervised learning is frequently used to initialize the parameters of the model when we have a lot of unlabeled data and a small fraction of labeled data. We first train an unsupervised model and, after that, we use the weights of the model to train a supervised model. In reinforcement learning, the model has some input data and a reward depending on the output of the model. The model learns a policy that maximizes the reward. Reinforcement learning has been applied successfully to strategic games such as Go and even classic Atari video games.

**What is the reason for the popularity of Deep Learning in recent times? **

Now although Deep Learning has been around for many years, the major breakthroughs from these techniques came just in recent years. This is because of two main reasons:

• The increase in the amount of data generated through various sources

• The growth in hardware resources required to run these models

GPUs are multiple times faster and they help us build bigger and deeper deep learning models in comparatively less time than we required previously

Machine Learning For Dummies App

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What is reinforcement learning?**

Reinforcement Learning allows to take actions to max cumulative reward. It learns by trial and error through reward/penalty system. Environment rewards agent so by time agent makes better decisions.

Ex: robot=agent, maze=environment. Used for complex tasks (self-driving cars, game AI).

RL is a series of time steps in a Markov Decision Process:

1. Environment: space in which RL operates

2. State: data related to past action RL took

3. Action: action taken

4. Reward: number taken by agent after last action

5. Observation: data related to environment: can be visible or partially shadowed

**Explain Ensemble learning.**

In ensemble learning, many base models like classifiers and regressors are generated and combined together so that they give better results. It is used when we build component classifiers that are accurate and independent. There are sequential as well as parallel ensemble methods.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What are the parametric models? Give an example.**

Parametric models are those with a finite number of parameters. To predict new data, you only need to know the parameters of the model. Examples include linear regression, logistic regression, and linear SVMs.

Non-parametric models are those with an unbounded number of parameters, allowing for more flexibility. To predict new data, you need to know the parameters of the model and the state of the data that has been observed. Examples include decision trees, k-nearest neighbors, and topic models using latent Dirichlet analysis.

**What are support vector machines?**

Support vector machines are supervised learning algorithms used for classification and regression analysis.

**What is batch statistical learning?**

Statistical learning techniques allow learning a function or predictor from a set of observed data that can make predictions about unseen or future data. These techniques provide guarantees on the performance of the learned predictor on the future unseen data based on a statistical assumption on the data generating process.

**What Will Happen If the Learning Rate is Set inaccurately (Too Low or Too High)?**

When your learning rate is too low, training of the model will progress very slowly as we are making minimal updates to the weights. It will take many updates before reaching the minimum point.

If the learning rate is set too high, this causes undesirable divergent behavior to the loss function due to drastic updates in weights. It may fail to converge (model can give a good output) or even diverge (data is too chaotic for the network to train).

**What Is The Difference Between Epoch, Batch, and Iteration in Deep Learning? **

• **Epoch** – Represents one iteration over the entire dataset (everything put into the training model).

• **Batch** – Refers to when we cannot pass the entire dataset into the neural network at once, so we divide the dataset into several batches.

• **Iteration** – if we have 10,000 images as data and a batch size of 200. then an epoch should run 50 iterations (10,000 divided by 50).

**Why Is Tensorflow the Most Preferred Library in Deep Learning?**

Tensorflow provides both C++ and Python APIs, making it easier to work on and has a faster compilation time compared to other Deep Learning libraries like Keras and Torch. Tensorflow supports both CPU and GPU computing devices.

**What Do You Mean by Tensor in Tensorflow?**

A tensor is a mathematical object represented as arrays of higher dimensions. These arrays of data with different dimensions and ranks fed as input to the neural network are called “Tensors.”

**Explain a Computational Graph.**

Everything in TensorFlow is based on creating a computational graph. It has a network of nodes where each node operates, Nodes represent mathematical operations, and edges represent tensors. Since data flows in the form of a graph, it is also called a “DataFlow Graph.”

**Cognition: Reasoning on top of data (Regression, Classification, Pattern Recognition)**

**What is the difference between classification and regression?**

Classification is used to produce discrete results, classification is used to classify data into some specific categories. For example, classifying emails into spam and non-spam categories.

Whereas, We use regression analysis when we are dealing with continuous data, for example predicting stock prices at a certain point in time.

**Explain the Bias-Variance Tradeoff.**

Predictive models have a tradeoff between bias (how well the model fits the data) and variance (how much the model changes based on changes in the inputs).

Simpler models are stable (low variance) but they don’t get close to the truth (high bias).

More complex models are more prone to overfitting (high variance) but they are expressive enough to get close to the truth (low bias). The best model for a given problem usually lies somewhere in the middle.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What is the difference between stochastic gradient descent (SGD) and gradient descent (GD)?**

Both algorithms are methods for finding a set of parameters that minimize a loss function by evaluating parameters against data and then making adjustments.

In standard gradient descent, you’ll evaluate all training samples for each set of parameters.

This is akin to taking big, slow steps toward the solution.

In stochastic gradient descent, you’ll evaluate only 1 training sample for the set of parameters before updating them. This is akin to taking small, quick steps toward the solution.

**How Can You Choose a Classifier Based on a Training Set Data Size?**

When the training set is small, a model that has a right bias and low variance seems to work better because they are less likely to overfit. For example, Naive Bayes works best when the training set is large. Models with low bias and high variance tend to perform better as they work fine with complex relationships.

**Explain Latent Dirichlet Allocation (LDA)**

Latent Dirichlet Allocation (LDA) is a common method of topic modeling, or classifying documents by subject matter.

LDA is a generative model that represents documents as a mixture of topics that each have their own probability distribution of possible words.

The “Dirichlet” distribution is simply a distribution of distributions. In LDA, documents are distributions of topics that are distributions of words.

**Explain Principle Component Analysis (PCA)**

PCA is a method for transforming features in a dataset by combining them into uncorrelated linear combinations.

These new features, or principal components, sequentially maximize the variance represented (i.e. the first principal component has the most variance, the second principal component has the second most, and so on).

As a result, PCA is useful for dimensionality reduction because you can set an arbitrary variance cutoff.

**PCA is a dimensionality reduction technique** that enables you to identify the correlations and patterns in the dataset so that it can be transformed into a dataset of significantly lower dimensions without any loss of important information.

• It is an unsupervised statistical technique used to examine the interrelations among a set of variables. It is also known as a general factor analysis where regression determines a line of best fit.

• It works on a condition that while the data in a higher-dimensional space is mapped to data in a lower dimension space, the variance or spread of the data in the lower dimensional space should be maximum.

**PCA is carried out in the following steps**

1. Standardization of Data

2. Computing the covariance matrix

3. Calculation of the eigenvectors and eigenvalues

4. Computing the Principal components

5. Reducing the dimensions of the Data.

**Reference: Here**

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What’s the F1 score? How would you use it?**

The F1 score is a measure of a model’s performance. It is a weighted average of the precision and recall of a model, with results tending to 1 being the best, and those tending to 0 being the worst. You would use it in classification tests where true negatives don’t matter much.

**When should you use classification over regression?**

Classification produces discrete values and dataset to strict categories, while regression gives you continuous results that allow you to better distinguish differences between individual points.

You would use classification over regression if you wanted your results to reflect the belongingness of data points in your dataset to certain explicit categories (ex: If you wanted to know whether a name was male or female rather than just how correlated they were with male and female names.)

**How do you ensure you’re not overfitting with a model?**

This is a simple restatement of a fundamental problem in machine learning: the possibility of overfitting training data and carrying the noise of that data through to the test set, thereby providing inaccurate generalizations.

There are three main methods to avoid overfitting:

1- Keep the model simpler: reduce variance by taking into account fewer variables and parameters, thereby removing some of the noise in the training data.

2- Use cross-validation techniques such as k-folds cross-validation.

3- Use regularization techniques such as LASSO that penalize certain model parameters if they’re likely to cause overfitting.

**How Will You Know Which Machine Learning Algorithm to Choose for Your Classification Problem?**

While there is no fixed rule to choose an algorithm for a classification problem, you can follow these guidelines:

● If accuracy is a concern, test different algorithms and cross-validate them

● If the training dataset is small, use models that have low variance and high bias

● If the training dataset is large, use models that have high variance and little bias

**Why is Area Under ROC Curve (AUROC) better than raw accuracy as an out-of-sample evaluation metric?**

AUROC is robust to class imbalance, unlike raw accuracy.

For example, if you want to detect a type of cancer that’s prevalent in only 1% of the population, you can build a model that achieves 99% accuracy by simply classifying everyone has cancer-free.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What are the advantages and disadvantages of neural networks?**

Advantages: Neural networks (specifically deep NNs) have led to performance breakthroughs for unstructured datasets such as images, audio, and video. Their incredible flexibility allows them to learn patterns that no other ML algorithm can learn.

Disadvantages: However, they require a large amount of training data to converge. It’s also difficult to pick the right architecture, and the internal “hidden” layers are incomprehensible.

**Define Precision and Recall.**

Precision

● Precision is the ratio of several events you can correctly recall to the total number of events you recall (mix of correct and wrong recalls).

● Precision = (True Positive) / (True Positive + False Positive)

Recall

● A recall is the ratio of a number of events you can recall the number of total events.

● Recall = (True Positive) / (True Positive + False Negative)

**What Is Decision Tree Classification?**

A decision tree builds classification (or regression) models as a tree structure, with datasets broken up into ever-smaller subsets while developing the decision tree, literally in a tree-like way with branches and nodes. Decision trees can handle both categorical and numerical data.

**What Is Pruning in Decision Trees, and How Is It Done?**

Pruning is a technique in machine learning that reduces the size of decision trees. It reduces the complexity of the final classifier, and hence improves predictive accuracy by the reduction of overfitting.

Pruning can occur in:

● Top-down fashion. It will traverse nodes and trim subtrees starting at the root

● Bottom-up fashion. It will begin at the leaf nodes

There is a popular pruning algorithm called reduced error pruning, in which:

● Starting at the leaves, each node is replaced with its most popular class

● If the prediction accuracy is not affected, the change is kept

● There is an advantage of simplicity and speed

**What Is a Recommendation System?**

Anyone who has used Spotify or shopped at Amazon will recognize a recommendation system:

It’s an information filtering system that predicts what a user might want to hear or see based on choice patterns provided by the user.

**What Is Kernel SVM?**

Kernel SVM is the abbreviated version of the kernel support vector machine. Kernel methods are a class of algorithms for pattern analysis, and the most common one is the kernel SVM.

What Are Some Methods of Reducing Dimensionality?

You can reduce dimensionality by combining features with feature engineering, removing collinear features, or using algorithmic dimensionality reduction.

Now that you have gone through these machine learning interview questions, you must have got an idea of your strengths and weaknesses in this domain.

**How is KNN different from k-means clustering?**

K-Nearest Neighbors is a supervised classification algorithm, while k-means clustering is an unsupervised clustering algorithm. While the mechanisms may seem similar at first, what this really means is that in order for K-Nearest Neighbors to work, you need labeled data you want to classify an unlabeled point into (thus the nearest neighbor part). K-means clustering requires only a set of unlabeled points and a threshold: the algorithm will take unlabeled points and gradually learn how to cluster them into groups by computing the mean of the distance between different points.

**What are difference between Data Mining and Machine learning?**

Machine learning relates to the study, design, and development of the algorithms that give computers the capability to learn without being explicitly programmed. While data mining can be defined as the process in which the unstructured data tries to extract knowledge or unknown interesting patterns. During this processing machine, learning algorithms are used.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What is “Naive” in a Naive Bayes?**

Reference: Naive Bayes Classifier on Wikipedia

Naive Bayes methods are a set of supervised learning algorithms based on applying Bayes’ theorem with the “naive” assumption of conditional independence between every pair of features given the value of the class variable. Bayes’ theorem states the following relationship, given class variable y and dependent feature vector X1through Xn:

**What is PCA (Principal Component Analysis)? When do you use it?**

Reference: PCA on wikipedia

Principal component analysis (PCA) is a statistical method used in Machine Learning. It consists in projecting data in a higher dimensional space into a lower dimensional space by maximizing the variance of each dimension.

The process works as following. We define a matrix A with > rows (the single observations of a dataset – in a tabular format, each single row) and @ columns, our features. For this matrix we construct a variable space with as many dimensions as there are features. Each feature represents one coordinate axis. For each feature, the length has been standardized according to a scaling criterion, normally by scaling to unit variance. It is determinant to scale the features to a common scale, otherwise the features with a greater magnitude will weigh more in determining the principal components. Once plotted all the observations and computed the mean of each variable, that mean will be represented by a point in the center of our plot (the center of gravity). Then, we subtract each observation with the mean, shifting the coordinate system with the center in the origin. The best fitting line resulting is the line that best accounts for the shape of the point swarm. It represents the maximum variance direction in the data. Each observation may be projected onto this line in order to get a coordinate value along the PC-line. This value is known as a score. The next best-fitting line can be similarly chosen from directions perpendicular to the first.

Repeating this process yields an orthogonal basis in which different individual dimensions of the data are uncorrelated. These basis vectors are called principal components.

PCA is mostly used as a tool in exploratory data analysis and for making predictive models. It is often used to visualize genetic distance and relatedness between populations.

**What are the pre-processing steps required for performing principal component analysis on a dataset?**

PCA is a technique that is used for reducing the dimensionality of a dataset while still preserving as much of the variance as possible. It is commonly used in machine learning and data science, as it can help to improve the performance of models by making the data easier to work with. In order to perform PCA on a dataset, there are a few pre-processing steps that need to be undertaken.

- First, any features that are strongly correlated with each other should be removed, as PCA will not be effective in reducing the dimensionality of the data if there are strong correlations present.
- Next, any features that contain missing values should be imputed, as PCA cannot be performed on data that contains missing values.
- Finally, the data should be scaled so that all features are on the same scale; this is necessary because PCA is based on the variance of the data, and if the scales of the features are different then PCA will not be able to accurately identify which features are most important in terms of variance.
- Once these pre-processing steps have been completed, PCA can be performed on the dataset.

Principal component analysis (PCA) is a statistical technique that is used to reduce the dimensionality of a dataset. PCA is often used as a pre-processing step in machine learning and data science, as it can help to improve the performance of models. In order to perform PCA on a dataset, the data must first be scaled and centered. Scaling ensures that all of the features are on the same scale, which is important for PCA. Centering means that the mean of each feature is zero. This is also important for PCA, as PCA is sensitive to changes in the mean of the data. Once the data has been scaled and centered, PCA can be performed by computing the eigenvectors and eigenvalues of the covariance matrix. These eigenvectors and eigenvalues can then be used to transform the data into a lower-dimensional space.

**SVM (Support Vector Machine) algorithm**

Reference: SVM on wikipedia

Classifying data is a common task in machine learning. Suppose some given data points each belong to one of two classes, and the goal is to decide which class a new data point will be in. In the case of supportvector machines, a data point is viewed as a p-dimensional vector (a list of p numbers), and we want to know whether we can separate such points with a (p − 1)-dimensional hyperplane. This is called a linear classifier. There are many hyperplanes that might classify the data. One reasonable choice as the best hyperplane is the one that represents the largest separation, or margin, between the two classes. So, we

choose the hyperplane so that the distance from it to the nearest data point on each side is maximized. If such a hyperplane exists, it is known as the maximum-margin hyperplane and the linear classifier it defines is known as a maximum-margin classifier; or equivalently, the perceptron of optimal stability. The best hyper plane that divides the data is H_{3.}

- SVMs are helpful in text and hypertext categorization, as their application can significantly reduce the need for labeled training instances in both the standard inductive and transductive settings.
- Some methods for shallow semantic parsing are based on support vector machines.
- Classification of images can also be performed using SVMs. Experimental results show that SVMs achieve significantly higher search accuracy than traditional query refinement schemes after just three to four rounds of relevance feedback.
- Classification of satellite data like SAR data using supervised SVM.
- Hand-written characters can be recognized using SVM.

**What are the support vectors in SVM? **

In the diagram, we see that the sketched lines mark the distance from the classifier (the hyper plane) to the closest data points called the support vectors (darkened data points). The distance between the two thin lines is called the margin.

To extend SVM to cases in which the data are not linearly separable, we introduce the hinge loss function, max (0, 1 – y_{i}(w∙ x_{i} − b)). This function is zero if x lies on the correct side of the margin. For data on the wrong side of the margin, the function’s value is proportional to the distance from the margin.

**What are the different kernels in SVM?**

There are four types of kernels in SVM.

1. LinearKernel

2. Polynomial kernel

3. Radial basis kernel

4. Sigmoid kernel

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What are the most known ensemble algorithms?**

Reference: Ensemble Algorithms

The most popular trees are: AdaBoost, Random Forest, and eXtreme Gradient Boosting (XGBoost).

AdaBoost is best used in a dataset with low noise, when computational complexity or timeliness of results is not a main concern and when there are not enough resources for broader hyperparameter tuning due to lack of time and knowledge of the user.

Random forests should not be used when dealing with time series data or any other data where look-ahead bias should be avoided, and the order and continuity of the samples need to be ensured. This algorithm can handle noise relatively well, but more knowledge from the user is required to adequately tune the algorithm compared to AdaBoost.

The main advantages of XGBoost is its lightning speed compared to other algorithms, such as AdaBoost, and its regularization parameter that successfully reduces variance. But even aside from the regularization parameter, this algorithm leverages a learning rate (shrinkage) and subsamples from the features like random forests, which increases its ability to generalize even further. However, XGBoost is more difficult to understand, visualize and to tune compared to AdaBoost and random forests. There is a multitude of hyperparameters that can be tuned to increase performance.

**What are Artificial Neural Networks?**

Artificial Neural networks are a specific set of algorithms that have revolutionized machine learning. They are inspired by biological neural networks. Neural Networks can adapt to changing the input, so the network generates the best possible result without needing to redesign the output criteria.

Artificial Neural Networks works on the same principle as a biological Neural Network. It consists of inputs which get processed with weighted sums and Bias, with the help of Activation Functions.

**How Are Weights Initialized in a Network?**

There are two methods here: we can either initialize the weights to zero or assign them randomly.

Initializing all weights to 0: This makes your model similar to a linear model. All the neurons and every layer perform the same operation, giving the same output and making the deep net useless.

Initializing all weights randomly: Here, the weights are assigned randomly by initializing them very close to 0. It gives better accuracy to the model since every neuron performs different computations. This is the most commonly used method.

**What Is the Cost Function? **

Also referred to as “loss” or “error,” cost function is a measure to evaluate how good your model’s performance is. It’s used to compute the error of the output layer during backpropagation. We push that error backwards through the neural network and use that during the different training functions.

The most known one is the mean sum of squared errors.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What Are Hyperparameters?**

With neural networks, you’re usually working with hyperparameters once the data is formatted correctly.

A hyperparameter is a parameter whose value is set before the learning process begins. It determines how a network is trained and the structure of the network (such as the number of hidden units, the learning rate, epochs, batches, etc.).

**What Are the Different Layers on CNN?**

Reference: Layers of CNN

The Convolutional neural networks are regularized versions of multilayer perceptron (MLP). They were developed based on the working of the neurons of the animal visual cortex.

**The objective of using the CNN:**

The idea is that you give the computer this array of numbers and it will output numbers that describe the probability of the image being a certain class (.80 for a cat, .15 for a dog, .05 for a bird, etc.). It works similar to how our brain works. When we look at a picture of a dog, we can classify it as such if the picture has identifiable features such as paws or 4 legs. In a similar way, the computer is able to perform image classification by looking for low-level features such as edges and curves and then building up to more abstract concepts through a series of convolutional layers. The computer uses low-level features obtained at the initial levels to generate high-level features such as paws or eyes to identify the object.

**There are four layers in CNN:**

1. Convolutional Layer – the layer that performs a convolutional operation, creating several smaller picture windows to go over the data.

2. Activation Layer (ReLU Layer) – it brings non-linearity to the network and converts all the negative pixels to zero. The output is a rectified feature map. It follows each convolutional layer.

3. Pooling Layer – pooling is a down-sampling operation that reduces the dimensionality of the feature map. Stride = how much you slide, and you get the max of the n x n matrix

4. Fully Connected Layer – this layer recognizes and classifies the objects in the image.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What Is Pooling on CNN, and How Does It Work?**

Pooling is used to reduce the spatial dimensions of a CNN. It performs down-sampling operations to reduce the dimensionality and creates a pooled feature map by sliding a filter matrix over the input matrix.

**What are Recurrent Neural Networks (RNNs)? **

Reference: RNNs

RNNs are a type of artificial neural networks designed to recognize the pattern from the sequence of data such as Time series, stock market and government agencies etc.

Recurrent Neural Networks (RNNs) add an interesting twist to basic neural networks. A vanilla neural network takes in a fixed size vector as input which limits its usage in situations that involve a ‘series’ type input with no predetermined size.

RNNs are designed to take a series of input with no predetermined limit on size. One could ask what’s\ the big deal, I can call a regular NN repeatedly too?

Sure can, but the ‘series’ part of the input means something. A single input item from the series is related to others and likely has an influence on its neighbors. Otherwise it’s just “many” inputs, not a “series” input (duh!).

Recurrent Neural Network remembers the past and its decisions are influenced by what it has learnt from the past. Note: Basic feed forward networks “remember” things too, but they remember things they learnt during training. For example, an image classifier learns what a “1” looks like during training and then uses that knowledge to classify things in production.

While RNNs learn similarly while training, in addition, they remember things learnt from prior input(s) while generating output(s). RNNs can take one or more input vectors and produce one or more output vectors and the output(s) are influenced not just by weights applied on inputs like a regular NN, but also by a “hidden” state vector representing the context based on prior input(s)/output(s). So, the same input could produce a different output depending on previous inputs in the series.

In summary, in a vanilla neural network, a fixed size input vector is transformed into a fixed size output vector. Such a network becomes “recurrent” when you repeatedly apply the transformations to a series of given input and produce a series of output vectors. There is no pre-set limitation to the size of the vector. And, in addition to generating the output which is a function of the input and hidden state, we update the hidden state itself based on the input and use it in processing the next input.

**What is the role of the Activation Function?**

The Activation function is used to introduce non-linearity into the neural network helping it to learn more complex function. Without which the neural network would be only able to learn linear function which is a linear combination of its input data. An activation function is a function in an artificial neuron that delivers an output based on inputs.

**Machine Learning libraries for various purposes**

**What is an Auto-Encoder?**

Reference: Auto-Encoder

Auto-encoders are simple learning networks that aim to transform inputs into outputs with the minimum possible error. This means that we want the output to be as close to input as possible. We add a couple of layers between the input and the output, and the sizes of these layers are smaller than the input layer. The auto-encoder receives unlabeled input which is then encoded to reconstruct the input.

An autoencoder is a type of artificial neural network used to learn efficient data coding in an unsupervised manner. The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for dimensionality reduction, by training the network to ignore signal “noise”. Along with the reduction side, a reconstructing side is learnt, where the autoencoder tries to generate from the reduced encoding a representation as close as possible to its original input, hence its name. Several variants exist to the basic model, with the aim of forcing the learned representations of the input to assume useful properties.

Autoencoders are effectively used for solving many applied problems, from face recognition to acquiring the semantic meaning of words.

**What is a Boltzmann Machine?**

Boltzmann machines have a simple learning algorithm that allows them to discover interesting features that represent complex regularities in the training data. The Boltzmann machine is basically used to optimize the weights and the quantity for the given problem. The learning algorithm is very slow in networks with many layers of feature detectors. “Restricted Boltzmann Machines” algorithm has a single layer of feature detectors which makes it faster than the rest.

**What Is Dropout and Batch Normalization?**

Dropout is a technique of dropping out hidden and visible nodes of a network randomly to prevent overfitting of data (typically dropping 20 per cent of the nodes). It doubles the number of iterations needed to converge the network. It used to avoid overfitting, as it increases the capacity of generalization.

Batch normalization is the technique to improve the performance and stability of neural networks by normalizing the inputs in every layer so that they have mean output activation of zero and standard deviation of one

**Why Is TensorFlow the Most Preferred Library in Deep Learning?**

TensorFlow provides both C++ and Python APIs, making it easier to work on and has a faster compilation time compared to other Deep Learning libraries like Keras and PyTorch. TensorFlow supports both CPU and GPU computing devices.

**What is Tensor in TensorFlow?**

A tensor is a mathematical object represented as arrays of higher dimensions. Think of a n-D matrix. These arrays of data with different dimensions and ranks fed as input to the neural network are called “Tensors.”

**What is the Computational Graph?**

Everything in a TensorFlow is based on creating a computational graph. It has a network of nodes where each node operates. Nodes represent mathematical operations, and edges represent tensors. Since data flows in the form of a graph, it is also called a “DataFlow Graph.”

**How is logistic regression done? **

Logistic regression measures the relationship between the dependent variable (our label of what we want to predict) and one or more independent variables (our features) by estimating probability using its underlying logistic function (sigmoid).

**Explain the steps in making a decision tree. **

1. Take the entire data set as input

2. Calculate entropy of the target variable, as well as the predictor attributes

3. Calculate your information gain of all attributes (we gain information on sorting different objects from each other)

4. Choose the attribute with the highest information gain as the root node

5. Repeat the same procedure on every branch until the decision node of each branch is finalized

For example, let’s say you want to build a decision tree to decide whether you should accept or decline a job offer. The decision tree for this case is as shown:

It is clear from the decision tree that an offer is accepted if:

• Salary is greater than $50,000

• The commute is less than an hour

• Coffee is offered

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**How do you build a random forest model?**

A random forest is built up of a number of decision trees. If you split the data into different packages and make a decision tree in each of the different groups of data, the random forest brings all those trees together.

Steps to build a random forest model:

1. Randomly select ; features from a total of = features where k<< m

2. Among the ; features, calculate the node D using the best split point

3. Split the node into daughter nodes using the best split

4. Repeat steps two and three until leaf nodes are finalized

5. Build forest by repeating steps one to four for > times to create > number of trees

**Differentiate between univariate, bivariate, and multivariate analysis. **

**Univariate data** contains only one variable. The purpose of the univariate analysis is to describe the data and find patterns that exist within it.

The patterns can be studied by drawing conclusions using mean, median, mode, dispersion or range, minimum, maximum, etc.

**Bivariate data** involves two different variables. The analysis of this type of data deals with causes and relationships and the analysis is done to determine the relationship between the two variables.

Here, the relationship is visible from the table that temperature and sales are directly proportional to each other. The hotter the temperature, the better the sales.

**Multivariate data** involves three or more variables, it is categorized under multivariate. It is similar to a bivariate but contains more than one dependent variable.

**Example: data for house price prediction**

The patterns can be studied by drawing conclusions using mean, median, and mode, dispersion or range, minimum, maximum, etc. You can start describing the data and using it to guess what the price of the house will be.

**What are the feature selection methods used to select the right variables?**

There are two main methods for feature selection.**Filter Methods**

This involves:

• Linear discrimination analysis

• ANOVA

• Chi-Square

The best analogy for selecting features is “bad data in, bad answer out.” When we’re limiting or selecting the features, it’s all about cleaning up the data coming in.

**Wrapper Methods**

This involves:

• Forward Selection: We test one feature at a time and keep adding them until we get a good fit

• Backward Selection: We test all the features and start removing them to see what works

better

• Recursive Feature Elimination: Recursively looks through all the different features and how they pair together

**Wrapper methods are very labor-intensive**, and high-end computers are needed if a lot of data analysis is performed with the wrapper method.

**You are given a data set consisting of variables with more than 30 percent missing values. How will you deal with them? **

If the data set is large, we can just simply remove the rows with missing data values. It is the quickest way; we use the rest of the data to predict the values.

For smaller data sets, we can impute missing values with the mean, median, or average of the rest of the data using pandas data frame in python. There are different ways to do so, such as: df.mean(), df.fillna(mean)

Other option of imputation is using KNN for numeric or classification values (as KNN just uses k closest values to impute the missing value).

Q76: How will you calculate the Euclidean distance in Python?

plot1 = [1,3]

plot2 = [2,5]

The Euclidean distance can be calculated as follows:

**euclidean_distance** = sqrt((plot1[0]-plot2[0])**2 + (plot1[1]- plot2[1])**2)

**What are dimensionality reduction and its benefits? **

Dimensionality reduction refers to the process of converting a data set with vast dimensions into data with fewer dimensions (fields) to convey similar information concisely.

This reduction helps in compressing data and reducing storage space. It also reduces computation time as fewer dimensions lead to less computing. It removes redundant features; for example, there’s no point in storing a value in two different units (meters and inches).

**How should you maintain a deployed model?**

The steps to maintain a deployed model are (CREM):

**1. Monitor:** constant monitoring of all models is needed to determine their performance accuracy.

When you change something, you want to figure out how your changes are going to affect things.

This needs to be monitored to ensure it’s doing what it’s supposed to do.**2. Evaluate:** evaluation metrics of the current model are calculated to determine if a new algorithm is needed.**3. Compare:** the new models are compared to each other to determine which model performs the best.**4. Rebuild:** the best performing model is re-built on the current state of data.

**How can a time-series data be declared as stationery?**

- The mean of the series should not be a function of time.

- The variance of the series should not be a function of time. This property is known as homoscedasticity.

- The covariance of the i th term and the (i+m) th term should not be a function of time.

**‘People who bought this also bought…’ recommendations seen on Amazon are a result of which algorithm?**

The recommendation engine is accomplished with **collaborative filtering**. Collaborative filtering explains the behavior of other users and their purchase history in terms of ratings, selection, etc.

The engine makes predictions on what might interest a person based on the preferences of other users. In this algorithm, item features are unknown.

For example, a sales page shows that a certain number of people buy a new phone and also buy tempered glass at the same time. Next time, when a person buys a phone, he or she may see a recommendation to buy tempered glass as well.

** What is a Generative Adversarial Network?**

Suppose there is a wine shop purchasing wine from dealers, which they resell later. But some dealers sell fake wine. In this case, the shop owner should be able to distinguish between fake and authentic wine. The forger will try different techniques to sell fake wine and make sure specific techniques go past the shop owner’s check. The shop owner would probably get some feedback from wine experts that some of the wine is not original. The owner would have to improve how he determines whether a wine is fake or authentic.

The forger’s goal is to create wines that are indistinguishable from the authentic ones while the shop owner intends to tell if the wine is real or not accurately.

• There is a noise vector coming into the forger who is generating fake wine.

• Here the forger acts as a Generator.

• The shop owner acts as a Discriminator.

• The Discriminator gets two inputs; one is the fake wine, while the other is the real authentic wine.

The shop owner has to figure out whether it is real or fake.

So, there are two primary components of Generative Adversarial Network (GAN) named:

1. Generator

2. Discriminator

The generator is a CNN that keeps keys producing images and is closer in appearance to the real images while the discriminator tries to determine the difference between real and fake images. The ultimate aim is to make the discriminator learn to identify real and fake images.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**You are given a dataset on cancer detection. You have built a classification model and achieved an accuracy of 96 percent. Why shouldn’t you be happy with your model performance? What can you do about it?**

Cancer detection results in imbalanced data. In an imbalanced dataset, accuracy should not be based as a measure of performance. It is important to focus on the remaining four percent, which represents the patients who were wrongly diagnosed. Early diagnosis is crucial when it comes to cancer detection and can greatly improve a patient’s prognosis.

Hence, to evaluate model performance, we should use Sensitivity (True Positive Rate), Specificity (True Negative Rate), F measure to determine the class wise performance of the classifier.

**We want to predict the probability of death from heart disease based on three risk factors: age, gender, and blood cholesterol level. What is the most appropriate algorithm for this case?**

The most appropriate algorithm for this case is l**ogistic regression**.

**After studying the behavior of a population, you have identified four specific individual types that are valuable to your study. You would like to find all users who are most similar to each individual type. Which algorithm is most appropriate for this study? **

As we are looking for grouping people together specifically by four different similarities, it indicates the value of k. Therefore, **K-means clustering** is the most appropriate algorithm for this study.

**You have run the association rules algorithm on your dataset, and the two rules {banana, apple} => {grape} and {apple, orange} => {grape} have been found to be relevant. What else must be true? **

**{grape, apple}** must be a frequent itemset.

**Your organization has a website where visitors randomly receive one of two coupons. It is also possible that visitors to the website will not receive a coupon. You have been asked to determine if offering a coupon to website visitors has any impact on their purchase decisions. Which analysis method should you use?**

**One-way ANOVA**: in statistics, one-way analysis of variance is a technique that can be used to compare means of two or more samples. This technique can be used only for numerical response data, the “Y”, usually one variable, and numerical or categorical input data, the “X”, always one variable, hence “oneway”.**The ANOVA tests the null hypothesis**, which states that samples in all groups are drawn from populations with the same mean values. To do this, two estimates are made of the population variance. **The ANOVA produces an F-statistic**, the ratio of the variance calculated among the means to the variance within the samples. If the group means are drawn from populations with the same mean values, the variance between the group means should be lower than the variance of the samples, following the central limit

theorem. A higher ratio therefore implies that the samples were drawn from populations with different mean values.

**What are the feature vectors?**

**A feature vector is an n-dimensional vector of numerical features that represent an object.** In machine learning, **feature vectors** are used to represent numeric or symbolic characteristics (called features) of an object in a mathematical way that’s easy to analyze.

**What is root cause analysis?**

Root cause analysis was initially developed to analyze industrial accidents but is now widely used in other areas. It is a **problem-solving technique used for isolating the root causes of faults or problems**. A factor is called a root cause if its deduction from the problem-fault-sequence averts the final undesirable event from recurring.

**Do gradient descent methods always converge to similar points?**

They do not, because in some cases, they reach a local minimum or a local optimum point. You would not reach the global optimum point. This is governed by the data and the starting conditions.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What are the different Deep Learning Frameworks?**

• **PyTorch**: PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook’s AI Research lab. It is free and open-source software released under the Modified BSD license.

• **TensorFlow**: TensorFlow is a free and open-source software library for dataflow and differentiable programming across a range of tasks. It is a symbolic math library and is also used for machine learning applications such as neural networks. Licensed by Apache License 2.0. Developed by Google Brain Team.

• **Microsoft Cognitive Toolkit**: Microsoft Cognitive Toolkit describes neural networks as a series of computational steps via a directed graph.

• **Keras**: Keras is an open-source neural-network library written in Python. It is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, R, Theano, or PlaidML. Designed to enable fast experimentation with deep neural networks, it focuses on being user-friendly, modular, and extensible. Licensed by MIT.

**What are the different Deep Learning Frameworks?**

• **PyTorch**: PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook’s AI Research lab. It is free and open-source software released under the Modified BSD license.

• **TensorFlow**: TensorFlow is a free and open-source software library for dataflow and differentiable programming across a range of tasks. It is a symbolic math library and is also used for machine learning applications such as neural networks. Licensed by Apache License 2.0. Developed by Google Brain Team.

• **Microsoft Cognitive Toolkit**: Microsoft Cognitive Toolkit describes neural networks as a series of computational steps via a directed graph.

• **Keras**: Keras is an open-source neural-network library written in Python. It is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, R, Theano, or PlaidML. Designed to enable fast experimentation with deep neural networks, it focuses on being user-friendly, modular, and extensible. Licensed by MIT.

**How Does an LSTM Network Work?**

Reference: LTSM

Long-Short-Term Memory (LSTM) is a special kind of recurrent neural network capable of learning long-term dependencies, remembering information for long periods as its default behavior. There are three steps in an LSTM network:

• Step 1: The network decides what to forget and what to remember.

• Step 2: It selectively updates cell state values.

• Step 3: The network decides what part of the current state makes it to the output.

**What Is a Multi-layer Perceptron (MLP)?**

Reference: MLP

As in Neural Networks, MLPs have an input layer, a hidden layer, and an output layer. It has the same structure as a single layer perceptron with one or more hidden layers.

**Perceptron is a single layer neural network** and a multi-layer perceptron is called Neural Networks.

A (single layer) perceptron is a single layer neural network that works as a linear binary classifier. Being a single layer neural network, it can be trained without the use of more advanced algorithms like back propagation and instead can be trained by “stepping towards” your error in steps specified by a learning rate. When someone says perceptron, I usually think of the single layer version.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What is exploding gradients? **

While training an RNN, if you see exponentially growing (very large) error gradients which accumulate and result in very large updates to neural network model weights during training, they’re known as exploding gradients. At an extreme, the values of weights can become so large as to overflow and result in NaN values. The explosion occurs through exponential growth by repeatedly multiplying gradients through the network layers that have values larger than 1.0.

This has the effect of your model is unstable and unable to learn from your training data.

There are some subtle signs that you may be suffering from exploding gradients during the training of your network, such as:

• The model is unable to get traction on your training data (e.g. poor loss).

• The model is unstable, resulting in large changes in loss from update to update.

• The model loss goes to NaN during training.

• The model weights quickly become very large during training.

• The error gradient values are consistently above 1.0 for each node and layer during training.

**Solutions****1. Re-Design the Network Model:**

a. In deep neural networks, exploding gradients may be addressed by redesigning the

network to have fewer layers. There may also be some benefit in using a smaller batch

size while training the network.

b. In RNNs, updating across fewer prior time steps during training, called truncated

Backpropagation through time, may reduce the exploding gradient problem.

**2. Use Long Short-Term Memory Networks:** In RNNs, exploding gradients can be reduced by using the Long Short-Term Memory (LSTM) memory units and perhaps related gated-type neuron structures. Adopting LSTM memory units is a new best practice for recurrent neural networks for sequence prediction.

**3. Use Gradient Clipping:** Exploding gradients can still occur in very deep Multilayer Perceptron networks with a large batch size and LSTMs with very long input sequence lengths. If exploding gradients are still occurring, you can check for and limit the size of gradients during the training of your network. This is called gradient clipping. Specifically, the values of the error gradient are checked against a threshold value and clipped or set to that threshold value if the error gradient exceeds the threshold.

**4. Use Weight Regularization:** another approach, if exploding gradients are still occurring, is to check the size of network weights and apply a penalty to the networks loss function for large weight values. This is called weight regularization and often an L1 (absolute weights) or an L2 (squared weights) penalty can be used.

**What is vanishing gradients? **

While training an RNN, your slope can become either too small; this makes the training difficult. When the slope is too small, the problem is known as a Vanishing Gradient. It leads to long training times, poor performance, and low accuracy.

• Hyperbolic tangent and Sigmoid/Soft-max suffer vanishing gradient.

• RNNs suffer vanishing gradient, LSTM no (so it is perfect to predict stock prices). In fact, the propagation of error through previous layers makes the gradient get smaller so the weights are not updated.

**Solutions**

1. **Choose RELU**

2. **Use LSTM (for RNNs)**

3. **Use ResNet (Residual Network)** → after some layers, add x again: F(x) → ⋯ → F(x) + x

4. **Multi-level hierarchy**: pre-train one layer at the time through unsupervised learning, then fine-tune via backpropagation

5. **Gradient checking**: debugging strategy used to numerically track and assess gradients during training.

**What is Gradient Descent?**

Let’s first explain what a gradient is. **A gradient is a mathematical function.** When calculated on a point of a function, it gives the hyperplane (or slope) of the directions in which the function increases more. The gradient vector can be interpreted as the “direction and rate of fastest increase”. If the gradient of a function is non-zero at a point p, the direction of the gradient is the direction in which the function increases most quickly from p, and the magnitude of the gradient is the rate of increase in that direction.

Further, the gradient is the zero vector at a point if and only if it is a stationary point (where the derivative vanishes).

In Data Science, it simply measures the change in all weights with regard to the change in error, as we are partially derivating by w the loss function.

**Gradient descent is a first-order iterative optimization algorithm for finding the minimum of a function.**

The goal of the gradient descent is to minimize a given function which, in our case, is the loss function of the neural network. To achieve this goal, it performs two steps iteratively.

1. Compute the slope (gradient) that is the first-order derivative of the function at the current point

2. Move-in the opposite direction of the slope increase from the current point by the computed amount

So, the idea is to pass the training set through the hidden layers of the neural network and then update the parameters of the layers by computing the gradients using the training samples from the training dataset.

Think of it like this. Suppose a man is at top of the valley and he wants to get to the bottom of the valley.

So, he goes down the slope. He decides his next position based on his current position and stops when he gets to the bottom of the valley which was his goal.

• Gradient descent is an iterative optimization algorithm that is popular and it is a base for many other optimization techniques, which tries to obtain minimal loss in a model by tuning the weights/parameters in the objective function.

• Types of Gradient Descent:

- Batch Gradient Descent
- Stochastic Gradient Descent
- Mini Batch Gradient Descent

• Steps to achieve minimal loss:

- The first stage in gradient descent is to pick a starting value (a starting point) for w1, which is set to 0 by many algorithms.
- The gradient descent algorithm then calculates the gradient of the loss curve at the starting point.
- The gradient always points in the direction of steepest increase in the loss function. The gradient descent algorithm takes a step in the direction of the negative gradient in order to reduce loss as quickly as possible.
- To determine the next point along the loss function curve, the gradient descent algorithm adds some fraction of the gradient’s magnitude to the starting point and moves forward.
- The gradient descent then repeats this process, edging ever closer to the minimum.

**What is vanishing gradients? **

While training an RNN, your slope can become either too small; this makes the training difficult. When the slope is too small, the problem is known as a Vanishing Gradient. It leads to long training times, poor performance, and low accuracy.

• Hyperbolic tangent and Sigmoid/Soft-max suffer vanishing gradient.

• RNNs suffer vanishing gradient, LSTM no (so it is perfect to predict stock prices). In fact, the propagation of error through previous layers makes the gradient get smaller so the weights are not updated.

**Solutions**

1. **Choose RELU**

2. **Use LSTM (for RNNs)**

3. **Use ResNet (Residual Network)** → after some layers, add x again: F(x) → ⋯ → F(x) + x

4. **Multi-level hierarchy**: pre-train one layer at the time through unsupervised learning, then fine-tune via backpropagation

5. **Gradient checking**: debugging strategy used to numerically track and assess gradients during training.

**What is Back Propagation and Explain it Works. **

Back propagation is a training algorithm used for neural network. In this method, we update the weights of each layer from the last layer recursively, with the formula:

It has the following steps:

• Forward Propagation of Training Data (initializing weights with random or pre-assigned values)

• Gradients are computed using output weights and target

• Back Propagate for computing gradients of error from output activation

• Update the Weights

**What are the variants of Back Propagation? **

Reference: Variants of back propagation

- Stochastic Gradient Descent: In Batch Gradient Descent we were considering all the examples for every step of Gradient Descent. But what if our dataset is very huge. Deep learning models crave for data. The more the data the more chances of a model to be good. Suppose our dataset has 5 million examples, then just to take one step the model will have to calculate the gradients of all the 5 million examples. This does not seem an efficient way. To tackle this problem, we have Stochastic Gradient Descent. In Stochastic Gradient Descent (SGD), we consider just one example at a time to take a single step. We do the following steps in one epoch for SGD:

1. Take an example

2. Feed it to Neural Network

3. Calculate its gradient

4. Use the gradient we calculated in step 3 to update the weights

5. Repeat steps 1–4 for all the examples in training dataset

Since we are considering just one example at a time the cost will fluctuate over the training examples and it will not necessarily decrease. But in the long run, you will see the cost decreasing with fluctuations. Also, because the cost is so fluctuating, it will never reach the minimum, but it will keep dancing around it. SGD can be used for larger datasets. It converges faster when the dataset is large as it causes updates to the parameters more frequently.

Stochastic Gradient Descent (SGD)

- Batch Gradient Descent: all the training data is taken into consideration to take a single step. We take the average of the gradients of all the training examples and then use that mean gradient to update our parameters. So that’s just one step of gradient descent in one epoch. Batch Gradient Descent is great for convex or relatively smooth error manifolds. In this case, we move somewhat directly towards an optimum solution. The graph of cost vs epochs is also quite smooth because we are averaging over all the gradients of training data for a single step. The cost keeps on decreasing over the epochs.

**Mini-batch Gradient Descent**: It’s one of the most popular optimization algorithms. It’s a variant of Stochastic Gradient Descent and here instead of single training example, mini batch of samples is used. Batch Gradient Descent can be used for smoother curves. SGD can be used when the dataset is large. Batch Gradient Descent converges directly to minima. SGD converges faster for larger datasets.

But, since in SGD we use only one example at a time, we cannot implement the vectorized implementation on it. This can slow down the computations. To tackle this problem, a mixture of Batch Gradient Descent and SGD is used. Neither we use all the dataset all at once nor we use the single example at a time. We use a batch of a fixed number of training examples which is less than the actual dataset and call it a mini-batch. Doing this helps us achieve the advantages of both the former variants we saw. So, after creating the mini-batches of fixed size, we do the following steps in one epoch:

1. Pick a mini-batch

2. Feed it to Neural Network

3. Calculate the mean gradient of the mini-batch

4. Use the mean gradient we calculated in step 3 to update the weights

5. Repeat steps 1–4 for the mini-batches we created

Just like SGD, the average cost over the epochs in mini-batch gradient descent fluctuates because we are averaging a small number of examples at a time. So, when we are using the mini-batch gradient descent we are updating our parameters frequently as well as we can use vectorized implementation for faster computations.

**While we continue to integrate ML systems in high-stakes environments such as medical settings, roads, command control centers, we need to ensure they do not cause the loss of life. How can you handle this?**

By focusing on the following, which includes everything outside of just developing SOTA models, as well inclusion of key stakeholders.

🔹Robustness: Create models that are resilient to adversaries, unusual situations, and Black Swan events

🔹Monitoring: Detect malicious use, monitor predictions, and discover unexpected model functionality

🔹Alignment: Build models that represent and safely optimize hard-to-specify human values

🔹External Safety: Use ML to address risks to how ML systems are handled, such as cyber attacks

Machine Learning Unsolved Problems_ n_SafetyDownload Unsolved Problems in ML Safety Here

**You are given a data set. The data set has missing values that spread along 1 standard deviation from the median. What percentage of data would remain unaffected? Why?**

Since the data is spread across the median, let’s assume it’s a normal distribution. We know, in a normal distribution, ~68% of the data lies in 1 standard deviation from mean (or mode, median), which leaves ~32% of the data unaffected. Therefore, ~32% of the data would remain unaffected by missing values.

**What are PCA, KPCA, and ICA used for?**

PCA (Principal Components Analysis), KPCA ( Kernel-based Principal Component Analysis) and ICA ( Independent Component Analysis) are important feature extraction techniques used for dimensionality reduction.

**What is the bias-variance decomposition of classification error in the ensemble method?**

The expected error of a learning algorithm can be decomposed into bias and variance. A bias term measures how closely the average classifier produced by the learning algorithm matches the target function. The variance term measures how much the learning algorithm’s prediction fluctuates for different training sets.

**When is Ridge regression favorable over Lasso regression?**

You can quote ISLR’s authors Hastie, Tibshirani who asserted that, in the presence of few variables with medium / large sized effect, use lasso regression. In presence of many variables with small/medium-sized effects, use ridge regression.

Conceptually, we can say, lasso regression (L1) does both variable selection and parameter shrinkage, whereas Ridge regression only does parameter shrinkage and end up including all the coefficients in the model. In the presence of correlated variables, ridge regression might be the preferred choice. Also, ridge regression works best in situations where the least square estimates have higher variance. Therefore, it depends on our model objective.

**You’ve built a random forest model with 10000 trees. You got delighted after getting training error as 0.00. But, the validation error is 34.23. What is going on? Haven’t you trained your model perfectly?**

The model has overfitted. Training error 0.00 means the classifier has mimicked the training data patterns to an extent, that they are not available in the unseen data. Hence, when this classifier was run on an unseen sample, it couldn’t find those patterns and returned predictions with higher error. In a random forest, it happens when we use a larger number of trees than necessary. Hence, to avoid this situation, we should tune the number of trees using cross-validation.

**What is a convex hull?**

In the case of linearly separable data, the convex hull represents the outer boundaries of the two groups of data points. Once the convex hull is created, we get maximum margin hyperplane (MMH) as a perpendicular bisector between two convex hulls. MMH is the line which attempts to create the greatest separation between two groups.

**What do you understand by Type I vs Type II error?**

Type I error is committed when the null hypothesis is true and we reject it, also known as a ‘False Positive’. Type II error is committed when the null hypothesis is false and we accept it, also known as ‘False Negative’.

In the context of the confusion matrix, we can say Type I error occurs when we classify a value as positive (1) when it is actually negative (0). Type II error occurs when we classify a value as negative (0) when it is actually positive(1).

**In k-means or kNN, we use euclidean distance to calculate the distance between nearest neighbors. Why not manhattan distance?**

We don’t use manhattan distance because it calculates distance horizontally or vertically only. It has dimension restrictions. On the other hand, the euclidean metric can be used in any space to calculate distance. Since the data points can be present in any dimension, euclidean distance is a more viable option.

**Example:** Think of a chessboard, the movement made by a bishop or a rook is calculated by manhattan distance because of their respective vertical & horizontal movements.

**Do you suggest that treating a categorical variable as a continuous variable would result in a better predictive model?**

For better predictions, the categorical variable can be considered as a continuous variable only when the variable is ordinal in nature.

**OLS is to linear regression what the maximum likelihood is logistic regression. Explain the statement.**

OLS and Maximum likelihood are the methods used by the respective regression methods to approximate the unknown parameter (coefficient) value. In simple words, Ordinary least square(OLS) is a method used in linear regression which approximates the parameters resulting in minimum distance between actual and predicted values. Maximum

Likelihood helps in choosing the values of parameters which maximizes the likelihood that the parameters are most likely to produce observed data.

**When does regularization becomes necessary in Machine Learning?**

Regularization becomes necessary when the model begins to overfit/underfit. This technique introduces a cost term for bringing in more features with the objective function. Hence, it tries to push the coefficients for many variables to zero and hence reduce the cost term. This helps to reduce model complexity so that the model can become better at predicting (generalizing).

**What is Linear Regression?**

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

Linear Regression is a supervised Machine Learning algorithm. It is used to find the linear relationship between the dependent and the independent variables for predictive analysis.

• Linear regression assumes that the relationship between the features and the target vector is approximately linear. That is, the effect of the features on the target vector is constant.

• In linear regression, the target variable y is assumed to follow a linear function of one or more predictor variables plus some random error. The machine learning task is to estimate the parameters of this equation which can be achieved in two ways:

• The first approach is through the lens of minimizing loss. A common practice in machine learning is to choose a loss function that defines how well a model with a given set of parameters estimates the observed data. The most common loss function for linear regression is squared error loss.

• The second approach is through the lens of maximizing the likelihood. Another common practice in machine learning is to model the target as a random variable whose distribution depends on one or more parameters, and then find the parameters that maximize its likelihood.

Credit: Vikram K.

**What is the Variance Inflation Factor?**

Variance Inflation Factor (VIF) is the estimate of the volume of multicollinearity in a collection of many regression variables.

VIF = Variance of the model / Variance of the model with a single independent variable

We have to calculate this ratio for every independent variable. If VIF is high, then it shows the high collinearity of the independent variables.

**We know that one hot encoding increases the dimensionality of a dataset, but label encoding doesn’t. How?**

When we use one-hot encoding, there is an increase in the dimensionality of a dataset. The reason for the increase in dimensionality is that, for every class in the categorical variables, it forms a different variable.

**What is a Decision Tree?**

A decision tree is used to explain the sequence of actions that must be performed to get the desired output. It is a hierarchical diagram that shows the actions.

**What is the Binarizing of data? How to Binarize?**

In most of the Machine Learning Interviews, apart from theoretical questions, interviewers focus on the implementation part. So, this ML Interview Questions focused on the implementation of the theoretical concepts.

Converting data into binary values on the basis of threshold values is known as the binarizing of data. The values that are less than the threshold are set to 0 and the values that are greater than the threshold are set to 1.

This process is useful when we have to perform feature engineering, and we can also use it for adding unique features.

**What is cross-validation?**

Cross-validation is essentially a technique used to assess how well a model performs on a new independent dataset. The simplest example of cross-validation is when you split your data into two groups: training data and testing data, where you use the training data to build the model and the testing data to test the model.

• Cross-validation is a resampling procedure used to evaluate machine learning models on a limited data sample. The procedure has a single parameter called k that refers to the number of groups that a given data sample is to be split into. As such, the procedure is often called k-fold cross-validation.

• Cross-validation is primarily used in applied machine learning to estimate the skill of a machine learning model on unseen data. That is, to use a limited sample in order to estimate how the model is expected to perform in general when used to make predictions on data not used during the training of the model.

• It is a popular method because it is simple to understand and because it generally results in a less biased or less optimistic estimate of the model skill than other methods, such as a simple train/test split.

• Procedure for K-Fold Cross Validation:

1. Shuffle the dataset randomly.

2. Split the dataset into k groups

3. For each unique group:

a. Take the group as a holdout or test data set

b. Take the remaining groups as a training data set

c. Fit a model on the training set and evaluate it on the test set

d. Retain the evaluation score and discard the model

4. Summarize the skill of the model using the sample of model evaluation scores

Credit: Vikram K.

**When would you use random forests Vs SVM and why?**

There are a couple of reasons why a random forest is a better choice of the model than a support vector machine:

● Random forests allow you to determine the feature importance. SVM’s can’t do this.

● Random forests are much quicker and simpler to build than an SVM.

● For multi-class classification problems, SVMs require a one-vs-rest method, which is less scalable and more memory intensive.

**What are the drawbacks of a linear model?**

There are a couple of drawbacks of a linear model:

● A linear model holds some strong assumptions that may not be true in the application. It assumes a linear relationship, multivariate normality, no or little multicollinearity, no auto-correlation, and homoscedasticity

● A linear model can’t be used for discrete or binary outcomes.

● You can’t vary the model flexibility of a linear model.

**While we continue to integrate ML systems in high-stakes environments such as medical settings, roads, command control centers, we need to ensure they do not cause the loss of life. How can you handle this?**

By focusing on the following, which includes everything outside of just developing SOTA models, as well inclusion of key stakeholders.

🔹Robustness: Create models that are resilient to adversaries, unusual situations, and Black Swan events

🔹Monitoring: Detect malicious use, monitor predictions, and discover unexpected model functionality

🔹Alignment: Build models that represent and safely optimize hard-to-specify human values

🔹External Safety: Use ML to address risks to how ML systems are handled, such as cyber attacks

Machine Learning Unsolved Problems_ n_SafetyDownload Unsolved Problems in ML Safety Here

**You are given a data set. The data set has missing values that spread along 1 standard deviation from the median. What percentage of data would remain unaffected? Why?**

Since the data is spread across the median, let’s assume it’s a normal distribution. We know, in a normal distribution, ~68% of the data lies in 1 standard deviation from mean (or mode, median), which leaves ~32% of the data unaffected. Therefore, ~32% of the data would remain unaffected by missing values.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What are PCA, KPCA, and ICA used for?**

PCA (Principal Components Analysis), KPCA ( Kernel-based Principal Component Analysis) and ICA ( Independent Component Analysis) are important feature extraction techniques used for dimensionality reduction.

**What are support vector machines?**

Support vector machines are supervised learning algorithms used for classification and regression analysis.

**What is batch statistical learning?**

Statistical learning techniques allow learning a function or predictor from a set of observed data that can make predictions about unseen or future data. These techniques provide guarantees on the performance of the learned predictor on the future unseen data based on a statistical assumption on the data generating process.

**What is the bias-variance decomposition of classification error in the ensemble method?**

The expected error of a learning algorithm can be decomposed into bias and variance. A bias term measures how closely the average classifier produced by the learning algorithm matches the target function. The variance term measures how much the learning algorithm’s prediction fluctuates for different training sets.

**When is Ridge regression favorable over Lasso regression?**

You can quote ISLR’s authors Hastie, Tibshirani who asserted that, in the presence of few variables with medium / large sized effect, use lasso regression. In presence of many variables with small/medium-sized effects, use ridge regression.

Conceptually, we can say, lasso regression (L1) does both variable selection and parameter shrinkage, whereas Ridge regression only does parameter shrinkage and end up including all the coefficients in the model. In the presence of correlated variables, ridge regression might be the preferred choice. Also, ridge regression works best in situations where the least square estimates have higher variance. Therefore, it depends on our model objective.

**You’ve built a random forest model with 10000 trees. You got delighted after getting training error as 0.00. But, the validation error is 34.23. What is going on? Haven’t you trained your model perfectly?**

The model has overfitted. Training error 0.00 means the classifier has mimicked the training data patterns to an extent, that they are not available in the unseen data. Hence, when this classifier was run on an unseen sample, it couldn’t find those patterns and returned predictions with higher error. In a random forest, it happens when we use a larger number of trees than necessary. Hence, to avoid this situation, we should tune the number of trees using cross-validation.

**What is a convex hull?**

In the case of linearly separable data, the convex hull represents the outer boundaries of the two groups of data points. Once the convex hull is created, we get maximum margin hyperplane (MMH) as a perpendicular bisector between two convex hulls. MMH is the line which attempts to create the greatest separation between two groups.

**What do you understand by Type I vs Type II error?**

Type I error is committed when the null hypothesis is true and we reject it, also known as a ‘False Positive’. Type II error is committed when the null hypothesis is false and we accept it, also known as ‘False Negative’.

In the context of the confusion matrix, we can say Type I error occurs when we classify a value as positive (1) when it is actually negative (0). Type II error occurs when we classify a value as negative (0) when it is actually positive(1).

**In k-means or kNN, we use euclidean distance to calculate the distance between nearest neighbors. Why not manhattan distance?**

We don’t use manhattan distance because it calculates distance horizontally or vertically only. It has dimension restrictions. On the other hand, the euclidean metric can be used in any space to calculate distance. Since the data points can be present in any dimension, euclidean distance is a more viable option.

**Example:** Think of a chessboard, the movement made by a bishop or a rook is calculated by manhattan distance because of their respective vertical & horizontal movements.

**Do you suggest that treating a categorical variable as a continuous variable would result in a better predictive model?**

For better predictions, the categorical variable can be considered as a continuous variable only when the variable is ordinal in nature.

**OLS is to linear regression wha the maximum likelihood is logistic regression. Explain the statement.**

OLS and Maximum likelihood are the methods used by the respective regression methods to approximate the unknown parameter (coefficient) value. In simple words, Ordinary least square(OLS) is a method used in linear regression which approximates the parameters resulting in minimum distance between actual and predicted values. Maximum

Likelihood helps in choosing the values of parameters which maximizes the likelihood that the parameters are most likely to produce observed data.

**When does regularization becomes necessary in Machine Learning?**

Regularization becomes necessary when the model begins to overfit/underfit. This technique introduces a cost term for bringing in more features with the objective function. Hence, it tries to push the coefficients for many variables to zero and hence reduce the cost term. This helps to reduce model complexity so that the model can become better at predicting (generalizing).

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What is Linear Regression?**

Linear Regression is a supervised Machine Learning algorithm. It is used to find the linear relationship between the dependent and the independent variables for predictive analysis.

**What is the Variance Inflation Factor?**

Variance Inflation Factor (VIF) is the estimate of the volume of multicollinearity in a collection of many regression variables.

VIF = Variance of the model / Variance of the model with a single independent variable

We have to calculate this ratio for every independent variable. If VIF is high, then it shows the high collinearity of the independent variables.

**We know that one hot encoding increases the dimensionality of a dataset, but label encoding doesn’t. How?**

When we use one-hot encoding, there is an increase in the dimensionality of a dataset. The reason for the increase in dimensionality is that, for every class in the categorical variables, it forms a different variable.

**What is a Decision Tree?**

A decision tree is used to explain the sequence of actions that must be performed to get the desired output. It is a hierarchical diagram that shows the actions.

**What is the Binarizing of data? How to Binarize?**

In most of the Machine Learning Interviews, apart from theoretical questions, interviewers focus on the implementation part. So, this ML Interview Questions focused on the implementation of the theoretical concepts.

Converting data into binary values on the basis of threshold values is known as the binarizing of data. The values that are less than the threshold are set to 0 and the values that are greater than the threshold are set to 1.

This process is useful when we have to perform feature engineering, and we can also use it for adding unique features.

**What is cross-validation?**

Cross-validation is essentially a technique used to assess how well a model performs on a new independent dataset. The simplest example of cross-validation is when you split your data into two groups: training data and testing data, where you use the training data to build the model and the testing data to test the model.

**When would you use random forests Vs SVM and why?**

There are a couple of reasons why a random forest is a better choice of the model than a support vector machine:

● Random forests allow you to determine the feature importance. SVM’s can’t do this.

● Random forests are much quicker and simpler to build than an SVM.

● For multi-class classification problems, SVMs require a one-vs-rest method, which is less scalable and more memory intensive.

**What are the drawbacks of a linear model?**

There are a couple of drawbacks of a linear model:

● A linear model holds some strong assumptions that may not be true in the application. It assumes a linear relationship, multivariate normality, no or little multicollinearity, no auto-correlation, and homoscedasticity

● A linear model can’t be used for discrete or binary outcomes.

● You can’t vary the model flexibility of a linear model.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**Do you think 50 small decision trees are better than a large one? Why?**

Another way of asking this question is “Is a random forest a better model than a decision tree?”

And the answer is yes because a random forest is an ensemble method that takes many weak decision trees to make a strong learner. Random forests are more accurate, more robust, and less prone to overfitting.

**What is a kernel? Explain the kernel trick**

A kernel is a way of computing the dot product of two vectors x and y in some (possibly very high dimensional) feature space, which is why kernel functions are sometimes called “generalized dot product”

The kernel trick is a method of using a linear classifier to solve a non-linear problem by transforming linearly inseparable data to linearly separable ones in a higher dimension.

**State the differences between causality and correlation?**

Causality applies to situations where one action, say X, causes an outcome, say Y, whereas Correlation is just relating one action (X) to another action(Y) but X does not necessarily cause Y.

**What is the exploding gradient problem while using the backpropagation technique?**

When large error gradients accumulate and result in large changes in the neural network weights during training, it is called the exploding gradient problem. The values of weights can become so large as to overflow and result in NaN values. This makes the model unstable and the learning of the model to stall just like the vanishing gradient problem.

**What do you mean by Associative Rule Mining (ARM)?**

Associative Rule Mining is one of the techniques to discover patterns in data like features (dimensions) which occur together and features (dimensions) which are correlated.

**What is Marginalization? Explain the process.**

Marginalization is summing the probability of a random variable X given the joint probability distribution of X with other variables. It is an application of the law of total probability.

**Why is the rotation of components so important in Principle Component Analysis(PCA)?**

Rotation in PCA is very important as it maximizes the separation within the variance obtained by all the components because of which interpretation of components would become easier. If the components are not rotated, then we need extended components to describe the variance of the components.

**What is the difference between regularization and normalization?**

Normalization adjusts the data; regularization adjusts the prediction function. If your data is on very different scales (especially low to high), you would want to normalize the data. Alter each column to have compatible basic statistics. This can be helpful to make sure there is no loss of accuracy. One of the goals of model training is to identify the signal and ignore the noise if the model is given free rein to minimize error, there is a possibility of suffering from overfitting.

Regularization imposes some control on this by providing simpler fitting functions over complex ones.

**How does the SVM algorithm deal with self-learning?**

SVM has a learning rate and expansion rate which takes care of this. The learning rate compensates or penalizes the hyperplanes for making all the wrong moves and expansion rate deals with finding the maximum separation area between classes.

**How do you handle outliers in the data?**

Outlier is an observation in the data set that is far away from other observations in the data set.

We can discover outliers using tools and functions like box plot, scatter plot, Z-Score, IQR score etc. and then handle them based on the visualization we have got. To handle outliers, we can cap at some threshold, use transformations to reduce skewness of the data and remove outliers if they are anomalies or errors.

**What are some techniques used to find similarities in the recommendation system?**

Pearson correlation and Cosine correlation are techniques used to find similarities in recommendation systems.

**Why would you Prune your tree?**

In the context of data science or AIML, pruning refers to the process of reducing redundant branches of a decision tree. Decision Trees are prone to overfitting, pruning the tree helps to reduce the size and minimizes the chances of overfitting. Pruning involves turning branches of a decision tree into leaf nodes and removing the leaf nodes from the original branch. It serves as a tool to perform the tradeoff.

**What are some of the EDA Techniques?**

Exploratory Data Analysis (EDA) helps analysts to understand the data better and forms the foundation of better models.

Visualization

● Univariate visualization

● Bivariate visualization

● Multivariate visualization

Missing Value Treatment – Replace missing values with Either Mean/Median Outlier Detection – Use Boxplot to identify the distribution of Outliers, then Apply IQR to set the boundary for IQR

**What is data augmentation?**

Data augmentation is a technique for synthesizing new data by modifying existing data in such a way that the target is not changed, or it is changed in a known way.

CV is one of the fields where data augmentation is very useful. There are many modifications that we can do to images:

● Resize

● Horizontal or vertical flip

● Rotate

● Add noise

● Deform

● Modify colors

Each problem needs a customized data augmentation pipeline. For example, on OCR, doing flips will change the text and won’t be beneficial; however, resizes and small rotations may **help.**

**What is Inductive Logic Programming in Machine Learning (ILP)?**

Inductive Logic Programming (ILP) is a subfield of machine learning which uses logic programming representing background knowledge and examples.

**What is the difference between inductive machine learning and deductive machine learning?**

The difference between inductive machine learning and deductive machine learning are as follows: machine-learning where the model learns by examples from a set of observed instances to draw a generalized conclusion whereas in deductive learning the model first draws the conclusion and then the conclusion is drawn.

**What is the Difference between machine learning and deep learning?**

Machine learning is a branch of computer science and a method to implement artificial intelligence. This technique provides the ability to automatically learn and improve from experiences without being explicitly programmed.

Deep learning can be said as a subset of machine learning. It is mainly based on the artificial neural network where data is taken as an input and the technique makes intuitive decisions using the artificial neural network.

**What Are The Steps Involved In Machine Learning Project?**

As you plan for doing a machine learning project. There are several important steps you must follow to achieve a good working model and they are **data collection, data preparation, choosing a machine learning model, training the model, model evaluation, parameter tuning and lastly prediction.**

**What are Differences between Artificial Intelligence and Machine Learning?**

Artificial intelligence is a broader prospect than machine learning. Artificial intelligence mimics the cognitive functions of the human brain. The purpose of AI is to carry out a task in an intelligent manner based on algorithms. On the other hand, machine learning is a subclass of artificial intelligence. To develop an autonomous machine in such a way so that it can learn without being explicitly programmed is the goal of machine learning.

**What are the steps Needed to choose the Appropriate Machine Learning Algorithm for your Classification problem?**

Firstly, you need to have a clear picture of your data, your constraints, and your problems before heading towards different machine learning algorithms. Secondly, you have to understand which type and kind of data you have because it plays a primary role in deciding which algorithm you have to use.

Following this step is the data categorization step, which is a two-step process – categorization by input and categorization by output. The next step is to understand your constraints; that is, what is your data storage capacity? How fast the prediction has to be? etc.

Finally, find the available machine learning algorithms and implement them wisely. Along with that, also try to optimize the hyperparameters which can be done in three ways – grid search, random search, and Bayesian optimization.

**What is the Convex Function?**

A convex function is a continuous function, and the value of the midpoint at every interval in its given domain is less than the numerical mean of the values at the two ends of the interval.

**What’s the Relationship between True Positive Rate and Recall?**

The True positive rate in machine learning is the percentage of the positives that have been properly acknowledged, and recall is just the count of the results that have been correctly identified and are relevant. Therefore, they are the same things, just having different names. It is also known as sensitivity.

**What are some tools for parallelizing Machine Learning Algorithms?**

Almost all machine learning algorithms are easy to serialize. Some of the basic tools for parallelizing are Matlab, Weka, R, Octave, or the Python-based sci-kit learn.

**What is meant by Genetic Programming?**

Genetic Programming (GP) is almost similar to an Evolutionary Algorithm, a subset of machine learning. Genetic programming software systems implement an algorithm that uses random mutation, a fitness function, crossover, and multiple generations of evolution to resolve a user-defined task. The genetic programming model is based on testing and choosing the best option among a set of results.

**What is meant by Bayesian Networks?**

Bayesian Networks also referred to as ‘belief networks’ or ‘casual networks’, are used to represent the graphical model for probability relationship among a set of variables.

For example, a Bayesian network can be used to represent the probabilistic relationships between diseases and symptoms. As per the symptoms, the network can also compute the probabilities of the presence of various diseases.

Efficient algorithms can perform inference or learning in Bayesian networks. Bayesian networks which relate the variables (e.g., speech signals or protein sequences) are called dynamic Bayesian networks.

**Which are the two components of the Bayesian logic program?**

A Bayesian logic program consists of two components:

● Logical It contains a set of Bayesian Clauses, which capture the qualitative structure of the domain.

● Quantitative It is used to encode quantitative information about the domain.

**How is machine learning used in day-to-day life?**

Most of the people are already using machine learning in their everyday life. Assume that you are engaging with the internet, you are actually expressing your preferences, likes, dislikes through your searches. All these things are picked up by cookies coming on your computer, from this, the behavior of a user is evaluated. It helps to increase the progress of a user through the internet and provide similar suggestions.

The navigation system can also be considered as one of the examples where we are using machine learning to calculate a distance between two places using optimization techniques.

**What is Sampling. Why do we need it?**

Sampling is a process of choosing a subset from a target population that would serve as its representative. We use the data from the sample to understand the pattern in the community as a whole. Sampling is necessary because often, we can not gather or process the complete data within a reasonable time.

**What does the term decision boundary mean?**

A decision boundary or a decision surface is a hypersurface which divides the underlying feature space into two subspaces, one for each class. If the decision boundary is a hyperplane, then the classes are linearly separable.

**Define entropy?**

Entropy is the measure of uncertainty associated with random variable Y. It is the expected number of bits required to communicate the value of the variable.

**Indicate the top intents of machine learning?**

The top intents of machine learning are stated below,

● The system gets information from the already established computations to give well-founded decisions and outputs.

● It locates certain patterns in the data and then makes certain predictions on it to provide answers on matters.

**Highlight the differences between the Generative model and the Discriminative model?**

The aim of the Generative model is to generate new samples from the same distribution and new data instances, Whereas, the Discriminative model highlights the differences between different kinds of data instances. It tries to learn directly from the data and then classifies the data.

**Identify the most important aptitudes of a machine learning engineer?**

Machine learning allows the computer to learn itself without being decidedly programmed. It helps the system to learn from experience and then improve from its mistakes. The intelligence system, which is based on machine learning, can learn from recorded data and past incidents.

In-depth knowledge of statistics, probability, data modelling, programming language, as well as CS, Application of ML Libraries and algorithms, and software design is required to become a successful machine learning engineer.

**What is feature engineering? How do you apply it in the process of modelling?**

Feature engineering is the process of transforming raw data into features that better represent the underlying problem to the predictive models, resulting in improved model accuracy on unseen data.

**How can learning curves help create a better model?**

Learning curves give the indication of the presence of overfitting or underfitting. In a learning curve, the training error and cross-validating error are plotted against the number of training data points.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**Perception: Vision, Audio, Speech, Natural Language**

**NLP: TF-IDF helps you to establish what?**

**List 10 use cases to be solved using NLP techniques?**

● Sentiment Analysis

● Language Translation (English to German, Chinese to English, etc..)

● Document Summarization

● Question Answering

● Sentence Completion

● Attribute extraction (Key information extraction from the documents)

● Chatbot interactions

● Topic classification

● Intent extraction

● Grammar or Sentence correction

● Image captioning

● Document Ranking

● Natural Language inference

**Which NLP model gives the best accuracy amongst the following: BERT, XLNET, GPT-2, ELMo**

XLNET has given best accuracy amongst all the models. It has outperformed BERT on 20 tasks and achieves state of art results on 18 tasks including sentiment analysis, question answering, natural language inference, etc.

**What is Naive Bayes algorithm, When we can use this algorithm in NLP?**

Naive Bayes algorithm is a collection of classifiers which works on the principles of the Bayes’theorem. This series of NLP model forms a family of algorithms that can be used for a wide range of classification tasks including sentiment prediction, filtering of spam, classifying documents and more.

Naive Bayes algorithm converges faster and requires less training data. Compared to other discriminative models like logistic regression, Naive Bayes model takes lesser time to train. This algorithm is perfect for use while working with multiple classes and text classification where the data is dynamic and changes frequently.

**Explain Dependency Parsing in NLP?**

Dependency Parsing, also known as Syntactic parsing in NLP is a process of assigning syntactic structure to a sentence and identifying its dependency parses. This process is crucial to understand the correlations between the “head” words in the syntactic structure.

The process of dependency parsing can be a little complex considering how any sentence can have more than one dependency parses. Multiple parse trees are known as ambiguities.

Dependency parsing needs to resolve these ambiguities in order to effectively assign a syntactic structure to a sentence.

Dependency parsing can be used in the semantic analysis of a sentence apart from the syntactic structuring.

**What is text Summarization?**

Text summarization is the process of shortening a long piece of text with its meaning and effect intact. Text summarization intends to create a summary of any given piece of text and outlines the main points of the document. This technique has improved in recent times and is capable of summarizing volumes of text successfully.

Text summarization has proved to a blessing since machines can summarize large volumes of text in no time which would otherwise be really time-consuming. There are two types of text summarization:

● Extraction-based summarization

● Abstraction-based summarization

**What is NLTK? How is it different from Spacy?**

NLTK or Natural Language Toolkit is a series of libraries and programs that are used for symbolic and statistical natural language processing. This toolkit contains some of the most powerful libraries that can work on different ML techniques to break down and understand human language. NLTK is used for Lemmatization, Punctuation, Character count, Tokenization, and Stemming.

The difference between NLTK and Spacey are as follows:

● While NLTK has a collection of programs to choose from, Spacey contains only the best suited algorithm for a problem in its toolkit

● NLTK supports a wider range of languages compared to Spacey (Spacey supports only 7 languages)

● While Spacey has an object-oriented library, NLTK has a string processing library

● Spacey can support word vectors while NLTK cannot

**What is information extraction?**

Information extraction in the context of Natural Language Processing refers to the technique of extracting structured information automatically from unstructured sources to ascribe meaning to it. This can include extracting information regarding attributes of entities, relationship between different entities and more. The various models of information extraction includes:

● Tagger Module

● Relation Extraction Module

● Fact Extraction Module

● Entity Extraction Module

● Sentiment Analysis Module

● Network Graph Module

● Document Classification & Language Modeling Module

**What is Bag of Words?**

Bag of Words is a commonly used model that depends on word frequencies or occurrences to train a classifier. This model creates an occurrence matrix for documents or sentences irrespective of its grammatical structure or word order.

**What is Pragmatic Ambiguity in NLP?**

Pragmatic ambiguity refers to those words which have more than one meaning and their use in any sentence can depend entirely on the context. Pragmatic ambiguity can result in multiple interpretations of the same sentence. More often than not, we come across sentences which have words with multiple meanings, making the sentence open to interpretation. This multiple interpretation causes ambiguity and is known as Pragmatic ambiguity in NLP.

**What is a Masked Language Model?**

Masked language models help learners to understand deep representations in downstream tasks by taking an output from the corrupt input. This model is often used to predict the words to be used in a sentence.

**What are the best NLP Tools?**

Some of the best NLP tools from open sources are:

● SpaCy

● TextBlob

● Textacy

● Natural language Toolkit

● Retext

● NLP.js

● Stanford NLP

● CogcompNLP

**What is POS tagging?**

Parts of speech tagging better known as POS tagging refers to the process of identifying specific words in a document and group them as part of speech, based on its context. POS tagging is also known as grammatical tagging since it involves understanding grammatical structures and identifying the respective component.

POS tagging is a complicated process since the same word can be different parts of speech depending on the context. The same generic process used for word mapping is quite ineffective for POS tagging because of the same reason.

**What is NES?**

Name entity recognition is more commonly known as NER is the process of identifying specific entities in a text document which are more informative and have a unique context. These often denote places, people, organizations, and more. Even though it seems like these entities are proper nouns, the NER process is far from identifying just the nouns. In fact, NER involves entity

chunking or extraction wherein entities are segmented to categorize them under different predefined classes. This step further helps in extracting information.

**Explain the Masked Language Model?**

Masked language modelling is the process in which the output is taken from the corrupted input.

This model helps the learners to master the deep representations in downstream tasks. You can predict a word from the other words of the sentence using this model.

**What is pragmatic analysis in NLP?**

Pragmatic Analysis: It deals with outside word knowledge, which means knowledge that is external to the documents and/or queries. Pragmatics analysis that focuses on what was described is reinterpreted by what it actually meant, deriving the various aspects of language that require real-world knowledge.

**What is perplexity in NLP?**

The word “perplexed” means “puzzled” or “confused”, thus Perplexity in general means the inability to tackle something complicated and a problem that is not specified. Therefore, Perplexity in NLP is a way to determine the extent of uncertainty in predicting some text.

In NLP, perplexity is a way of evaluating language models. Perplexity can be high and low; Low perplexity is ethical because the inability to deal with any complicated problem is less while high perplexity is terrible because the failure to deal with a complicated is high.

**What is ngram in NLP?**

N-gram in NLP is simply a sequence of n words, and we also conclude the sentences which appeared more frequently, for example, let us consider the progression of these three words:

● New York (2 gram)

● The Golden Compass (3 gram)

● She was there in the hotel (4 gram)

Now from the above sequence, we can easily conclude that sentence (a) appeared more frequently than the other two sentences, and the last sentence(c) is not seen that often. Now if we assign probability in the occurrence of an n-gram, then it will be advantageous. It would help in making next-word predictions and in spelling error corrections.

Explain differences between AI, Machine Learning and NLP

**Why self-attention is awesome?**

“In terms of computational complexity, self-attention layers are faster than recurrent layers when the sequence length n is smaller than the representation dimensionality d, which is most often the case with sentence representations used by state-of-the-art models in machine translations, such as word-piece and byte-pair representations.” — from Attention is all you need.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What are stop words?**

Stop words are said to be useless data for a search engine. Words such as articles, prepositions, etc. are considered as stop words. There are stop words such as was, were, is, am, the, a, an, how, why, and many more. In Natural Language Processing, we eliminate the stop words to understand and analyze the meaning of a sentence. The removal of stop words is one of the most important tasks for search engines. Engineers design the algorithms of search engines in such a way that they ignore the use of stop words. This helps show the relevant search result for a query.

**What is Latent Semantic Indexing (LSI)?**

Latent semantic indexing is a mathematical technique used to improve the accuracy of the information retrieval process. The design of LSI algorithms allows machines to detect the hidden (latent) correlation between semantics (words). To enhance information understanding, machines generate various concepts that associate with the words of a sentence.

The technique used for information understanding is called singular value decomposition. It is generally used to handle static and unstructured data. The matrix obtained for singular value decomposition contains rows for words and columns for documents. This method best suits to identify components and group them according to their types.

The main principle behind LSI is that words carry a similar meaning when used in a similar context.

Computational LSI models are slow in comparison to other models. However, they are good at contextual awareness that helps improve the analysis and understanding of a text or a document.

**What are Regular Expressions?**

A regular expression is used to match and tag words. It consists of a series of characters for matching strings.

Suppose, if A and B are regular expressions, then the following are true for them:

● If {ɛ} is a regular language, then ɛ is a regular expression for it.

● If A and B are regular expressions, then A + B is also a regular expression within the language {A, B}.

● If A and B are regular expressions, then the concatenation of A and B (A.B) is a regular expression.

● If A is a regular expression, then A* (A occurring multiple times) is also a regular expression.

**What are unigrams, bigrams, trigrams, and n-grams in NLP?**

When we parse a sentence one word at a time, then it is called a unigram. The sentence parsed two words at a time is a bigram.

When the sentence is parsed three words at a time, then it is a trigram. Similarly, n-gram refers to the parsing of n words at a time.

**What are the steps involved in solving an NLP problem?**

Below are the steps involved in solving an NLP problem:

1. Gather the text from the available dataset or by web scraping

2. Apply stemming and lemmatization for text cleaning

3. Apply feature engineering techniques

4. Embed using word2vec

5. Train the built model using neural networks or other Machine Learning techniques

6. Evaluate the model’s performance

7. Make appropriate changes in the model

8. Deploy the model

**There have some various common elements of natural language processing. Those elements are very important for understanding NLP properly, can you please explain the same in details with an example?**

There have a lot of components normally using by natural language processing (NLP). Some of the major components are explained below:

● Extraction of Entity: It actually identifying and extracting some critical data from the available information which help to segmentation of provided sentence on identifying each entity. It can help in identifying one human that it’s fictional or real, same kind of reality identification for any organization, events or any geographic location etc.

● The analysis in a syntactic way: it mainly helps for maintaining ordering properly of the available words.

**In the case of processing natural language, we normally mentioned one common terminology NLP and binding every language with the same terminology properly. Please explain in details about this NLP terminology with an example?**

This is the basic NLP Interview Questions asked in an interview. There have some several factors available in case of explaining natural language processing. Some of the key factors are given below:

● Vectors and Weights: Google Word vectors, length of TF-IDF, varieties documents, word vectors, TF-IDF.

● Structure of Text: Named Entities, tagging of part of speech, identifying the head of the sentence.

● Analysis of sentiment: Know about the features of sentiment, entities available for the sentiment, sentiment common dictionary.

● Classification of Text: Learning supervising, set off a train, set of validation in Dev, Set of define test, a feature of the individual text, LDA.

● Reading of Machine Language: Extraction of the possible entity, linking with an individual entity, DBpedia, some libraries like Pikes or FRED.

**Explain briefly about word2vec**

Word2Vec embeds words in a lower-dimensional vector space using a shallow neural network.

The result is a set of word-vectors where vectors close together in vector space have similar meanings based on context, and word-vectors distant to each other have differing meanings. For example, apple and orange would be close together and apple and gravity would be relatively far.

There are two versions of this model based on skip-grams (SG) and continuous-bag-of-words (CBOW).

**What are the metrics used to test an NLP model?**

Accuracy, Precision, Recall and F1. Accuracy is the usual ratio of the prediction to the desired output. But going just be accuracy is naive considering the complexities involved.

**What are some ways we can preprocess text input?**

Here are several preprocessing steps that are commonly used for NLP tasks:

● case normalization: we can convert all input to the same case (lowercase or uppercase) as a way of reducing our text to a more canonical form

● punctuation/stop word/white space/special characters removal: if we don’t think these words or characters are relevant, we can remove them to reduce the feature space

● lemmatizing/stemming: we can also reduce words to their inflectional forms (i.e. walks → walk) to further trim our vocabulary

● generalizing irrelevant information: we can replace all numbers with a <NUMBER> token or all names with a <NAME> token.

**How does the encoder-decoder structure work for language modelling?**

The encoder-decoder structure is a deep learning model architecture responsible for several state of the art solutions, including Machine Translation.

The input sequence is passed to the encoder where it is transformed to a fixed-dimensional vector representation using a neural network. The transformed input is then decoded using another neural network. Then, these outputs undergo another transformation and a SoftMax layer. The final output is a vector of probabilities over the vocabularies. Meaningful information is extracted based on these probabilities.

**How would you implement an NLP system as a service, and what are some pitfalls you might face in production?**

This is less of a NLP question than a question for productionizing machine learning models. There are however certain intricacies to NLP models.

Without diving too much into the productionization aspect, an ideal Machine Learning service will have:

● endpoint(s) that other business systems can use to make inference

● a feedback mechanism for validating model predictions

● a database to store predictions and ground truths from the feedback

● a workflow orchestrator which will (upon some signal) re-train and load the new model for

serving based on the records from the database + any prior training data

● some form of model version control to facilitate rollbacks in case of bad deployments

● post-production accuracy and error monitoring

**What are attention mechanisms and why do we use them?**

This was a follow-up to the encoder-decoder question. Only the output from the last time step is passed to the decoder, resulting in a loss of information learned at previous time steps. This information loss is compounded for longer text sequences with more time steps.

Attention mechanisms are a function of the hidden weights at each time step. When we use attention in encoder-decoder networks, the fixed-dimensional vector passed to the decoder becomes a function of all vectors outputted in the intermediary steps.

Two commonly used attention mechanisms are additive attention and multiplicative attention. As the names suggest, additive attention is a weighted sum while multiplicative attention is a weighted multiplier of the hidden weights. During the training process, the model also learns weights for the attention mechanisms to recognize the relative importance of each time step.

**How can we handle misspellings for text input?**

By using word embeddings trained over a large corpus (for instance, an extensive web scrape of billions of words), the model vocabulary would include common misspellings by design. The model can then learn the relationship between misspelled and correctly spelled words to recognize their semantic similarity.

We can also preprocess the input to prevent misspellings. Terms not found in the model vocabulary can be mapped to the “closest” vocabulary term using:

● edit distance between strings

● phonetic distance between word pronunciations

● keyword distance to catch common typos

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What is the problem with ReLu?**

● Exploding gradient(Solved by gradient clipping)

● Dying ReLu — No learning if the activation is 0 (Solved by parametric relu)

● Mean and variance of activations is not 0 and 1.(Partially solved by subtracting around 0.5 from activation. Better explained in fastai videos)

**What is the difference between learning latent features using SVD and getting embedding vectors using deep network?**

SVD uses linear combination of inputs while a neural network uses nonlinear combination.

**What is the information in the hidden and cell state of LSTM?**

Hidden stores all the information till that time step and cell state stores particular information that might be needed in the future time step.

**When is self-attention not faster than recurrent layers?**

When the sequence length is greater than the representation dimensions. This is rare.

**What is the benefit of learning rate warm-up?**

Learning rate warm-up is a learning rate schedule where you have low (or lower) learning rate at the beginning of training to avoid divergence due to unreliable gradients at the beginning. As the model becomes more stable, the learning rate would increase to speed up convergence.

**What’s the difference between hard and soft parameter sharing in multi-task learning?**

**What’s the difference between BatchNorm and LayerNorm?**

BatchNorm computes the mean and variance at each layer for every minibatch whereas LayerNorm computes the mean and variance for every sample for each layer independently.

Hard sharing is where we train for all the task at the same time and update our weights using all the losses whereas soft sharing is where we train for one task at a time.

Batch normalisation allows you to set higher learning rates, increasing speed of training as it reduces the unstability of initial starting weights.

**Difference between BatchNorm and LayerNorm?**

BatchNorm — Compute the mean and var at each layer for every minibatch

LayerNorm — Compute the mean and var for every single sample for each layer independently

**Why does the transformer block have LayerNorm instead of BatchNorm?**

Looking at the advantages of LayerNorm, it is robust to batch size and works better as it works at the sample level and not batch level.

**What changes would you make to your deep learning code if you knew there are errors in your training data?**

We can do label smoothening where the smoothening value is based on % error. If any particular class has known error, we can also use class weights to modify the loss.

What are the tricks used in ULMFiT? (Not a great questions but checks the awareness)

● LM tuning with task text

● Weight dropout

● Discriminative learning rates for layers

● Gradual unfreezing of layers

● Slanted triangular learning rate schedule

This can be followed up with a question on explaining how they help.

**Tell me a language model which doesn’t use dropout**

ALBERT v2 — This throws a light on the fact that a lot of assumptions we take for granted are not necessarily true. The regularization effect of parameter sharing in ALBERT is so strong that dropouts are not needed. (ALBERT v1 had dropouts.)

**What are the differences between GPT and GPT-2?**

● Layer normalization was moved to the input of each sub-block, similar to a residual unit of type “building block” (differently from the original type “bottleneck”, it has batch normalization applied before weight layers).

● An additional layer normalization was added after the final self-attention block.

● A modified initialization was constructed as a function of the model depth.

● The weights of residual layers were initially scaled by a factor of 1/√n where n is the number of residual layers.

● Use larger vocabulary size and context size.

**What are the differences between GPT and BERT?**

● GPT is not bidirectional and has no concept of masking

● BERT adds next sentence prediction task in training and so it also has a segment embedding

**What are the differences between BERT and ALBERT v2?**

● Embedding matrix factorisation(helps in reducing no. of parameters)

● No dropout

● Parameter sharing(helps in reducing no. of parameters and regularisation)

**How does parameter sharing in ALBERT affect the training and inference time?**

No effect. Parameter sharing just decreases the number of parameters.

**How would you reduce the inference time of a trained NN model?**

● Serve on GPU/TPU/FPGA

● 16 bit quantisation and served on GPU with fp16 support

● Pruning to reduce parameters

● Knowledge distillation (To a smaller transformer model or simple neural network)

● Hierarchical softmax/Adaptive softmax

● You can also cache results as explained here.

**Would you use BPE with classical models?**

Of course! BPE is a smart tokeniser and it can help us get a smaller vocabulary which can help us find a model with less parameters.

**How would you make an arxiv papers search engine? **

**How would you make a plagiarism detector?**

Get top k results with TF-IDF similarity and then rank results with

● semantic encoding + cosine similarity

● a model trained for ranking

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**How would you make a sentiment classifier?**

This is a trick question. The interviewee can say all things such as using transfer learning and latest models but they need to talk about having a neutral class too otherwise you can have really good accuracy/f1 and still, the model will classify everything into positive or negative.

The truth is that a lot of news is neutral and so the training needs to have this class. The interviewee should also talk about how he will create a dataset and his training strategies like the selection of language model, language model fine-tuning and using various datasets for multitask learning.

**What is the difference between regular expression and regular grammar?**

A regular expression is the representation of natural language in the form of mathematical expressions containing a character sequence. On the other hand, regular grammar is the generator of natural language, defining a set of defined rules and syntax which the strings in the natural language must follow.

**Why should we use Batch Normalization?**

Once the interviewer has asked you about the fundamentals of deep learning architectures, they would move on to the key topic of improving your deep learning model’s performance.

Batch Normalization is one of the techniques used for reducing the training time of our deep learning algorithm. Just like normalizing our input helps improve our logistic regression model, we can normalize the activations of the hidden layers in our deep learning model as well:

**How is backpropagation different in RNN compared to ANN?**

In Recurrent Neural Networks, we have an additional loop at each node:

This loop essentially includes a time component into the network as well. This helps in capturing sequential information from the data, which could not be possible in a generic artificial neural network.

This is why the backpropagation in RNN is called Backpropagation through Time, as in backpropagation at each time step.

**Which of the following is a challenge when dealing with computer vision problems?**

Variations due to geometric changes (like pose, scale, etc), Variations due to photometric factors (like illumination, appearance, etc) and Image occlusion. All the above-mentioned options are challenges in computer vision.

**Consider an image with width and height as 100×100. Each pixel in the image can have a color from Grayscale, i.e. values. How much space would this image require for storing?**

The answer will be 8x100x100 because 8 bits will be required to represent a number from 0-256

**Why do we use convolutions for images rather than just FC layers?**

Firstly, convolutions preserve, encode, and actually use the spatial information from the image. If we used only FC layers we would have no relative spatial information. Secondly, Convolutional Neural Networks (CNNs) have a partially built-in translation in-variance, since each convolution kernel acts as it’s own filter/feature detector

**What makes CNN’s translation-invariant?**

As explained above, each convolution kernel acts as it’s own filter/feature detector. So let’s say you’re doing object detection, it doesn’t matter where in the image the object is since we’re going to apply the convolution in a sliding window fashion across the entire image anyways.

**Why do we have max-pooling in classification CNNs?**

Max-pooling in a CNN allows you to reduce computation since your feature maps are smaller after the pooling. You don’t lose too much semantic information since you’re taking the maximum activation. There’s also a theory that max-pooling contributes a bit to giving CNN’s more translation in-variance. Check out this great video from Andrew Ng on the benefits of max-pooling.

**Why do segmentation CNN’s typically have an encoder-decoder style/structure?**

The encoder CNN can basically be thought of as a feature extraction network, while the decoder uses that information to predict the image segments by “decoding” the features and upscaling to the original image size.

**What is the significance of Residual Networks?**

The main thing that residual connections did was allow for direct feature access from previous layers. This makes information propagation throughout the network much easier. One very interesting paper about this shows how using local skip connections gives the network a type of ensemble multi-path structure, giving features multiple paths to propagate throughout the network.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What is batch normalization and why does it work?**

Training Deep Neural Networks is complicated by the fact that the distribution of each layer’s inputs changes during training, as the parameters of the previous layers change. The idea is then to normalize the inputs of each layer in such a way that they have a mean output activation of zero and a standard deviation of one. This is done for each individual mini-batch at each layer i.e compute the mean and variance of that mini-batch alone, then normalize. This is analogous to how the inputs to networks are standardized. How does this help? We know that normalizing the inputs to a network helps it learn.

But a network is just a series of layers, where the output of one layer becomes the input to the next. That means we can think of any layer in a neural network as the first layer of a smaller subsequent network. Thought of as a series of neural networks feeding into each other, we normalize the output of one layer before applying the activation function and then feed it into the following layer (sub-network).

**Why would you use many small convolutional kernels such as 3×3 rather than a few large ones?**

This is very well explained in the VGGNet paper.

There are 2 reasons: First, you can use several smaller kernels rather than few large ones to get the same receptive field and capture more spatial context, but with the smaller kernels you are using less parameters and computations. Secondly, because with smaller kernels you will be using more filters, you’ll be able to use more activation functions and thus have a more discriminative mapping function being learned by your CNN.

**What is Precision?**

Precision (also called positive predictive value) is the fraction of relevant instances among the retrieved instances

Precision = true positive / (true positive + false positive)

**What is Recall?**

Recall (also known as sensitivity) is the fraction of relevant instances that have been retrieved over the total amount of relevant instances.

Recall = true positive / (true positive + false negative)

**Define F1-score.**

It is the weighted average of precision and recall. It considers both false positive and false negatives into account. It is used to measure the model’s performance.

**What is cost function?**

The cost function is a scalar function that Quantifies the error factor of the Neural Network. Lower the cost function better than the Neural network. Eg: MNIST Data set to classify the image, the input image is digit 2 and the Neural network wrongly predicts it to be 3.

**List different activation neurons or functions**

● Linear Neuron

● Binary Threshold Neuron

● Stochastic Binary Neuron

● Sigmoid Neuron

● Tanh function

● Rectified Linear Unit (ReLU)

**Define Learning rate**

The learning rate is a hyper-parameter that controls how much we are adjusting the weights of our network with respect to the loss gradient.

**What is Momentum (w.r.t NN optimization)?**

Momentum lets the optimization algorithm remembers its last step, and adds some proportion of it to the current step. This way, even if the algorithm is stuck in a flat region, or a small local minimum, it can get out and continue towards the true minimum.

**What is the difference between Batch Gradient Descent and Stochastic Gradient Descent?**

Batch gradient descent computes the gradient using the whole dataset. This is great for convex or relatively smooth error manifolds. In this case, we move somewhat directly towards an optimum solution, either local or global. Additionally, batch gradient descent, given an annealed learning rate, will eventually find the minimum located in its basin of attraction.

Stochastic gradient descent (SGD) computes the gradient using a single sample. SGD works well (Not well, I suppose, but better than batch gradient descent) for error manifolds that have lots of local maxima/minima. In this case, the somewhat noisier gradient calculated using the reduced number of samples tends to jerk the model out of local minima into a region that hopefully is more optimal.

**Epoch vs Batch vs Iteration.**

Epoch: one forward pass and one backward pass of all the training examples

Batch: examples processed together in one pass (forward and backward)

Iteration: number of training examples / Batch size

**What is the vanishing gradient?**

As we add more and more hidden layers, backpropagation becomes less and less useful in passing information to the lower layers. In effect, as information is passed back, the gradients begin to vanish and become small relative to the weights of the networks.

**What are dropouts?**

Dropout is a simple way to prevent a neural network from overfitting. It is the dropping out of some of the units in a neural network. It is similar to the natural reproduction process, where nature produces offsprings by combining distinct genes (dropping out others) rather than strengthening the co-adapting of them.

**What is data augmentation? Can you give some examples?**

Data augmentation is a technique for synthesizing new data by modifying existing data in such a way that the target is not changed, or it is changed in a known way. Computer vision is one of the fields where data augmentation is very useful. There are many modifications that we can do to images:

● Resize

● Horizontal or vertical flip

● Rotate, Add noise, Deform

● Modify colors Each problem needs a customized data augmentation pipeline. For example, on OCR, doing flips will change the text and won’t be beneficial; however, resizes and small rotations may help.

**What are the components of GAN?**

● Generator

● Discriminator

**What’s the difference between a generative and discriminative model?**

A generative model will learn categories of data while a discriminative model will simply learn the distinction between different categories of data. Discriminative models will generally outperform generative models on classification tasks.

**What is Linear Filtering?**

Linear filtering is a neighborhood operation, which means that the output of a pixel’s value is decided by the weighted sum of the values of the input pixels.

**How can you achieve Blurring through Gaussian Filter?**

This is the most common technique for blurring or smoothing an image. This filter improves the resulting pixel found at the center and slowly minimizes the effects as pixels move away from the center. This filter can also help in removing noise in an image.

**How can you achieve Blurring through Gaussian Filter?**

This is the most common technique for blurring or smoothing an image. This filter improves the resulting pixel found at the center and slowly minimizes the effects as pixels move away from the center. This filter can also help in removing noise in an image.

**What is Non-Linear Filtering? How it is used?**

Linear filtering is easy to use and implement. In some cases, this method is enough to get the necessary output. However, an increase in performance can be obtained through non-linear filtering. Through non-linear filtering, we can have more control and achieve better results when we encounter a more complex computer vision task.

**Explain Median Filtering.**

The median filter is an example of a non-linear filtering technique. This technique is commonly used for minimizing the noise in an image. It operates by inspecting the image pixel by pixel and taking the place of each pixel’s value with the value of the neighboring pixel median.

Some techniques in detecting and matching features are:

● Lucas-Kanade

● Harris

● Shi-Tomasi

● SUSAN (smallest uni value segment assimilating nucleus)

● MSER (maximally stable extremal regions)

● SIFT (scale-invariant feature transform)

● HOG (histogram of oriented gradients)

● FAST (features from accelerated segment test)

● SURF (speeded-up robust features)

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**Describe the Scale Invariant Feature Transform (SIFT) algorithm**

SIFT solves the problem of detecting the corners of an object even if it is scaled. Steps to implement this algorithm:

● Scale-space extrema detection – This step will identify the locations and scales that can still be recognized from different angles or views of the same object in an image.

● Keypoint localization – When possible key points are located, they would be refined to get accurate results. This would result in the elimination of points that are low in contrast or points that have edges that are deficiently localized.

● Orientation assignment – In this step, a consistent orientation is assigned to each key point to attain invariance when the image is being rotated.

● Keypoint matching – In this step, the key points between images are now linked to recognizing their nearest neighbors.

**Why Speeded-Up Robust Features (SURF) came into existence?**

SURF was introduced to as a speed-up version of SIFT. Though SIFT can detect and describe key points of an object in an image, still this algorithm is slow.

**What is Oriented FAST and rotated BRIEF (ORB)?**

This algorithm is a great possible substitute for SIFT and SURF, mainly because it performs better in computation and matching. It is a combination of fast key point detector and brief descriptor, which contains a lot of alterations to improve performance. It is also a great alternative in terms of cost because the SIFT and SURF algorithms are patented, which means that you need to buy them for their utilization.

**What is image segmentation?**

In computer vision, segmentation is the process of extracting pixels in an image that is related.

Segmentation algorithms usually take an image and produce a group of contours (the boundary of an object that has well-defined edges in an image) or a mask where a set of related pixels are assigned to a unique color value to identify it.

Popular image segmentation techniques:

● Active contours

● Level sets

● Graph-based merging

● Mean Shift

● Texture and intervening contour-based normalized cuts

**What is the purpose of semantic segmentation?**

The purpose of semantic segmentation is to categorize every pixel of an image to a certain class or label. In semantic segmentation, we can see what is the class of a pixel by simply looking directly at the color, but one downside of this is that we cannot identify if two colored masks belong to a certain object.

**Explain instance segmentation.**

In semantic segmentation, the only thing that matters to us is the class of each pixel. This would somehow lead to a problem that we cannot identify if that class belongs to the same object or not.

Semantic segmentation cannot identify if two objects in an image are separate entities. So to solve this problem, instance segmentation was created. This segmentation can identify two different objects of the same class. For example, if an image has two sheep in it, the sheep will be detected and masked with different colors to differentiate what instance of a class they belong to.

**How is panoptic segmentation different from semantic/instance segmentation?**

Panoptic segmentation is basically a union of semantic and instance segmentation. In panoptic segmentation, every pixel is classified by a certain class and those pixels that have several instances of a class are also determined. For example, if an image has two cars, these cars will be masked with different colors. These colors represent the same class — car — but point to different instances of a certain class.

**Explain the problem of recognition in computer vision.**

Recognition is one of the toughest challenges in the concepts in computer vision. Why is recognition hard? For the human eyes, recognizing an object’s features or attributes would be very easy. Humans can recognize multiple objects with very small effort. However, this does not apply to a machine. It would be very hard for a machine to recognize or detect an object because these objects vary. They vary in terms of viewpoints, sizes, or scales. Though these things are still challenges faced by most computer vision systems, they are still making advancements or approaches for solving these daunting tasks.

**What is Object Recognition?**

Object recognition is used for indicating an object in an image or video. This is a product of machine learning and deep learning algorithms. Object recognition tries to acquire this innate human ability, which is to understand certain features or visual detail of an image.

**What is Object Detection and it’s real-life use cases?**

Object detection in computer vision refers to the ability of machines to pinpoint the location of an object in an image or video. A lot of companies have been using object detection techniques in their system. They use it for face detection, web images, and security purposes.

**Describe Optical Flow, its uses, and assumptions.**

Optical flow is the pattern of apparent motion of image objects between two consecutive frames caused by the movement of object or camera. It is a 2D vector field where each vector is a displacement vector showing the movement of points from the first frame to the second

Optical flow has many applications in areas like :

● Structure from Motion

● Video Compression

● Video Stabilization

Optical flow works on several assumptions:

1. The pixel intensities of an object do not change between consecutive frames.

2. Neighboring pixels have similar motion.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What is Histogram of Oriented Gradients (HOG)?**

HOG stands for Histograms of Oriented Gradients. HOG is a type of “feature descriptor”. The intent of a feature descriptor is to generalize the object in such a way that the same object (in this case a person) produces as close as possible to the same feature descriptor when viewed under different conditions. This makes the classification task easier.

**What’s the difference between valid and same padding in a CNN?**

This question has more chances of being a follow-up question to the previous one. Or if you have explained how you used CNNs in a computer vision task, the interviewer might ask this question along with the details of the padding parameters.

● Valid Padding: When we do not use any padding. The resultant matrix after convolution will have dimensions (n – f + 1) X (n – f + 1)

● Same padding: Adding padded elements all around the edges such that the output matrix will have the same dimensions as that of the input matrix

**What is BOV: Bag-of-visual-words (BOV)?**

BOV also called the bag of key points, is based on vector quantization. Similar to HOG features, BOV features are histograms that count the number of occurrences of certain patterns within a patch of the image.

**What is Poselets? Where are poselets used?**

Poselets rely on manually added extra keypoints such as “right shoulder”, “left shoulder”, “right knee” and “left knee”. They were originally used for human pose estimation

**Explain Textons in context of CNNs**

A texton is the minimal building block of vision. The computer vision literature does not give a strict definition for textons, but edge detectors could be one example. One might argue that deep learning techniques with Convolution Neuronal Networks (CNNs) learn textons in the first filters.

**What is Markov Random Fields (MRFs)?**

MRFs are undirected probabilistic graphical models which are a wide-spread model in computer vision. The overall idea of MRFs is to assign a random variable for each feature and a random variable for each pixel.

**Explain the concept of superpixel?**

A superpixel is an image patch that is better aligned with intensity edges than a rectangular patch.

Superpixels can be extracted with any segmentation algorithm, however, most of them produce highly irregular superpixels, with widely varying sizes and shapes. A more regular space tessellation may be desired.

**What is Non-maximum suppression(NMS) and where is it used?**

NMS is often used along with edge detection algorithms. The image is scanned along the image gradient direction, and if pixels are not part of the local maxima they are set to zero. It is widely used in object detection algorithms.

**Describe the use of Computer Vision in Healthcare.**

Computer vision has also been an important part of advances in health-tech. Computer vision algorithms can help automate tasks such as detecting cancerous moles in skin images or finding symptoms in x-ray and MRI scans

**Describe the use of Computer Vision in Augmented Reality & Mixed Reality**

Computer vision also plays an important role in augmented and mixed reality, the technology that enables computing devices such as smartphones, tablets, and smart glasses to overlay and embed virtual objects on real-world imagery. Using computer vision, AR gear detects objects in the real world in order to determine the locations on a device’s display to place a virtual object.

For instance, computer vision algorithms can help AR applications detect planes such as tabletops, walls, and floors, a very important part of establishing depth and dimensions and placing virtual objects in the physical world.

**Describe the use of Computer Vision in Facial Recognition**

Computer vision also plays an important role in facial recognition applications, the technology that enables computers to match images of people’s faces to their identities. Computer vision algorithms detect facial features in images and compare them with databases of face profiles.

Consumer devices use facial recognition to authenticate the identities of their owners. Social media apps use facial recognition to detect and tag users. Law enforcement agencies also rely on facial recognition technology to identify criminals in video feeds.

**Describe the use of Computer Vision in Self-Driving Cars**

Computer vision enables self-driving cars to make sense of their surroundings. Cameras capture video from different angles around the car and feed it to computer vision software, which then processes the images in real-time to find the extremities of roads, read traffic signs, detect other cars, objects, and pedestrians. The self-driving car can then steer its way on streets and highways, avoid hitting obstacles, and (hopefully) safely drive its passengers to their destination.

**Explain famous Computer Vision tasks using a single image example.**

Many popular computer vision applications involve trying to recognize things in photographs; for example:

Object Classification: What broad category of object is in this photograph?

Object Identification: Which type of a given object is in this photograph?

Object Verification: Is the object in the photograph?

Object Detection: Where are the objects in the photograph?

Object Landmark Detection: What are the key points for the object in the photograph?

Object Segmentation: What pixels belong to the object in the image?

Object Recognition: What objects are in this photograph and where are they?

**Explain the distinction between Computer Vision and Image Processing.**

Computer vision is distinct from image processing.

Image processing is the process of creating a new image from an existing image, typically simplifying or enhancing the content in some way. It is a type of digital signal processing and is not concerned with understanding the content of an image.

A given computer vision system may require image processing to be applied to raw input, e.g. pre-processing images.

Examples of image processing include:

● Normalizing photometric properties of the image, such as brightness or color.

● Cropping the bounds of the image, such as centering an object in a photograph.

● Removing digital noise from an image, such as digital artifacts from low light levels

**Explain business use cases in computer vision.**

● Optical character recognition (OCR)

● Machine inspection

● Retail (e.g. automated checkouts)

● 3D model building (photogrammetry)

● Medical imaging

● Automotive safety

● Match move (e.g. merging CGI with live actors in movies)

● Motion capture (mocap)

● Surveillance

● Fingerprint recognition and biometrics

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What is the Boltzmann Machine?**

One of the most basic Deep Learning models is a Boltzmann Machine, resembling a simplified version of the Multi-Layer Perceptron. This model features a visible input layer and a hidden layer — just a two-layer neural net that makes stochastic decisions as to whether a neuron should be on or off. Nodes are connected across layers, but no two nodes of the same layer are connected.

**What Is the Role of Activation Functions in a Neural Network?**

At the most basic level, an activation function decides whether a neuron should be fired or not. It accepts the weighted sum of the inputs and bias as input to any activation function. Step function,

Sigmoid, ReLU, Tanh, and Softmax are examples of activation functions.

**What Is the Difference Between a Feedforward Neural Network and Recurrent Neural Network?**

A Feedforward Neural Network signals travel in one direction from input to output. There are no feedback loops; the network considers only the current input. It cannot memorize previous inputs (e.g., CNN).

**What Are the Applications of a Recurrent Neural Network (RNN)?**

The RNN can be used for sentiment analysis, text mining, and image captioning. Recurrent Neural Networks can also address time series problems such as predicting the prices of stocks in a month or quarter.

**What Are the Softmax and ReLU Functions?**

Softmax is an activation function that generates the output between zero and one. It divides each output, such that the total sum of the outputs is equal to one. Softmax is often used for output layers.

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**Machine Learning Techniques**

**What Is Overfitting, and How Can You Avoid It?**

Overfitting is a situation that occurs when a model learns the training set too well, taking up random fluctuations in the training data as concepts. These impact the model’s ability to generalize and don’t apply to new data.

When a model is given the training data, it shows 100 percent accuracy—technically a slight loss. But, when we use the test data, there may be an error and low efficiency. This condition is known as overfitting.

There are multiple ways of avoiding overfitting, such as:

● Regularization. It involves a cost term for the features involved with the objective function

● Making a simple model. With lesser variables and parameters, the variance can be reduced

● Cross-validation methods like k-folds can also be used

● If some model parameters are likely to cause overfitting, techniques for regularization like LASSO can be used that penalize these parameters

**What is meant by ‘Training set’ and ‘Test Set’?**

We split the given data set into two different sections namely, ‘Training set’ and ‘Test Set’.

‘Training set’ is the portion of the dataset used to train the model.

‘Testing set’ is the portion of the dataset used to test the trained model.

**How Do You Handle Missing or Corrupted Data in a Dataset?**

One of the easiest ways to handle missing or corrupted data is to drop those rows or columns or replace them entirely with some other value.

There are two useful methods in Pandas:

● IsNull() and dropna() will help to find the columns/rows with missing data and drop them

● Fillna() will replace the wrong values with a placeholder value

**How Do You Design an Email Spam Filter?**

Building a spam filter involves the following process:

● The email spam filter will be fed with thousands of emails

● Each of these emails already has a label: ‘spam’ or ‘not spam.’

● The supervised machine learning algorithm will then determine which type of emails are being marked as spam based on spam words like the lottery, free offer, no money, full refund, etc.

● The next time an email is about to hit your inbox, the spam filter will use statistical analysis and algorithms like Decision Trees and SVM to determine how likely the email is spam

● If the likelihood is high, it will label it as spam, and the email won’t hit your inbox

● Based on the accuracy of each model, we will use the algorithm with the highest accuracy after testing all the models

**Explain bagging.**

Bagging, or Bootstrap Aggregating, is an ensemble method in which the dataset is first divided into multiple subsets through resampling.

Then, each subset is used to train a model, and the final predictions are made through voting or averaging the component models.

Bagging is performed in parallel.

**What is the ROC Curve and what is AUC (a.k.a. AUROC)?**

The ROC (receiver operating characteristic) the performance plot for binary classifiers of True Positive Rate (y-axis) vs. False Positive Rate (xaxis).

AUC is the area under the ROC curve, and it’s a common performance metric for evaluating binary classification models.

It’s equivalent to the expected probability that a uniformly drawn random positive is ranked before a uniformly drawn random negative.

**What are the various Machine Learning algorithms?**

**What is cross-validation?**

Reference: k-fold cross validation

**Cross-validation is a resampling procedure used to evaluate machine learning models on a limited data sample.** The procedure has a single parameter called k that refers to the number of groups that a given data sample is to be split into. As such, the procedure is often called k-fold cross-validation. When a specific value for k is chosen, it may be used in place of k in the reference to the model, such as k=10 becoming 10-fold cross-validation. Mainly used in backgrounds where the objective is forecast, and one wants to estimate how accurately a model will accomplish in practice.

Cross-validation is primarily used in applied machine learning to estimate the skill of a machine learning model on unseen data. That is, to use a limited sample in order to estimate how the model is expected to perform in general when used to make predictions on data not used during the training of the model.

It is a popular method because it is simple to understand and because it generally results in a less biased or less optimistic estimate of the model skill than other methods, such as a simple train/test split.

The general procedure is as follows:

1. Shuffle the dataset randomly.

2. Split the dataset into k groups

3. For each unique group:

a. Take the group as a hold out or test data set

b. Take the remaining groups as a training data set

c. Fit a model on the training set and evaluate it on the test set

d. Retain the evaluation score and discard the model

4. Summarize the skill of the model using the sample of model evaluation scores

**What are 3 data preprocessing techniques to handle outliers?**

1. Winsorize (cap at threshold).

2. Transform to reduce skew (using Box-Cox or similar).

3. Remove outliers if you’re certain they are anomalies or measurement errors.

**How much data should you allocate for your training, validation, and test sets?**

You have to find a balance, and there’s no right answer for every problem.

If your test set is too small, you’ll have an unreliable estimation of model performance (performance statistic will have high variance). If your training set is too small, your actual model parameters will have a high variance.

A good rule of thumb is to use an 80/20 train/test split. Then, your train set can be further split into train/validation or into partitions for cross-validation.

**What Is a False Positive and False Negative and How Are They Significant?**

False positives are those cases which wrongly get classified as True but are False.

False negatives are those cases which wrongly get classified as False but are True.

In the term ‘False Positive’, the word ‘Positive’ refers to the ‘Yes’ row of the predicted value in

the confusion matrix. The complete term indicates that the system has predicted it as a positive, but the actual value is negative.

**What’s a Fourier transform?**

A Fourier transform is a generic method to decompose generic functions into a superposition of symmetric functions. Or as this more intuitive tutorial puts it, given a smoothie, it’s how we find the recipe. The Fourier transform finds the set of cycle speeds, amplitudes, and phases to match any time signal. A Fourier transform converts a signal from time to frequency domain — it’s a very common way to extract features from audio signals or other time series such as sensor data.

**Machine Learning Cheat Sheets, Tutorial, Practical examples, References, Datasets**

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**Machine Learning Cheat Sheet**

Machine Learning Cheat Sheets**Credit: Remi Canard**

**TensorFlow Practical Examples and Tutorial**

– Basic Models

Linear Regression

Logistic Regression

Word2Vec (Word Embedding)

– Neural Networks

Simple Neural Network

Convolutional Neural Network

Recurrent Neural Network (LSTM)

Bi-directional Recurrent Neural Network (LSTM)

Dynamic Recurrent Neural Network (LSTM)

-Unsupervised

Auto-Encoder

DCGAN (Deep Convolutional Generative Adversarial Networks)

-Utilities:

Save and Restore a model

Build Custom Layers & Modules

– Data Management

Load and Parse data

Build and Load TFRecords

Image Transformation (i.e. Image Augmentation)

Credit: Alex Wang

**Cool MLOps repository of free talks, books, papers and more**

**Machine Learning Training Videos**

**References**

**1 https://springboard.com ****2 https://simplilearn.com ****3 https://geeksforgeeks.org ****4 https://elitedatascience.com ****5 https://analyticsvidhya.com ****6 https://guru99.com ****7 https://intellipaat.com ****8 https://towardsdatascience.com ****9 https://mygreatlearning.com****10 https://mindmajix.com ****11 https://toptal.com ****12 https://glassdoor.co.in ****13 https://udacity.com ****14 https://educba.com ****15 https://analyticsindiamag.com ****16 https://ubuntupit.com ****17 https://javatpoint.com ****18 https://quora.com ****19 hackr.io ****20 kaggle.com****21 https://www.linkedin.com/in/stevenouri/**

**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**Explain differences between AI, Machine Learning and NLP**

Artificial Intelligence | Machine Learning | Natural Language Processing |
---|---|---|

It is the technique t create smarter machines | Machine Learning is the term used for systems that learn from experience | This is the set of system that has the ability to understand the language |

AI includes human intervention | Machine Learning purely involves the working of computers and no human intervention | NLP links both computer and human languages |

Artificial intelligence is a broader concept than Machine Learning | ML is a narrow concept and is a subset of AI |

**Top Machine Learning Algorithms for Predictions:**

**TensorFlow Interview Questions and Answers**

Tensorflow Interview Questions and Answers**Machine Learning For Dummies on iOs**

**Machine Learning For Dummies on Windows**:

**Machine Learning For Dummies Web/Android**

**What are the most promising areas of machine learning research right now?**

Machine learning is just one component of a larger field called artificial intelligence (AI). AI researchers have done an excellent job at describing the fundamental problems they must solve to achieve intelligent behavior; these problems fall into four general categories: representation, reasoning, learning, and search.

Basically, all of AI research can be classified under these headings; for example, language understanding is a special case of representation (natural language), planning is a special case of reasoning (analogical logical inferences), learning to play chess is a special case of learning (policy search in the game tree), and table lookup is a special case of search (symbol-table lookups). We will focus on two: representation and search.

What follows are our ten favorite problems/areas for the next decade or so. Each one has been researched quite heavily already, but we think that there are no silver bullets yet discovered nor are there any obvious candidates lurking in the wings waiting to take over. Each area has a different flavor to it; all have something to offer the machine learning community, and we believe that many will find fertile ground for their own investigations.

Machine learning methods are useful on large problems, which is becoming increasingly important as applications such as speech recognition are moving into real-world situations outside the lab (e.g., using voice commands while driving). Solution: This is a difficult one because there are many possible solutions to this problem; all will require advances in both theoretical and experimental techniques but we do not know what they are yet. A better understanding of why certain learning algorithms work well on some types of problems but not others may provide insights into how to scale them up. Some examples of the types of problems we would like to tackle include: (i) learning from large databases, (ii) learning in multiple domains, and (iii) learning task-specific knowledge.

Artificial intelligence methods have been used to solve combinatorial problems such as chess playing and problem-solving; these are problems that can be represented as a search tree using nodes representing possible moves for each player. These methods work well on small problems but often fail when applied to larger real-world problems because there are too many options in the search trees that must be explored. For example, consider a game where there are 100 moves per second for each player with 10^100 different games possible over a 40 year lifetime. Solving the AI problem amounts to finding a winning strategy. This is much different from the type of problems we are used to solving which normally fit in memory and where the number of potential options can be kept manageable. Solution: We need better methods than those currently available for searching through very large trees; these could involve ideas from machine learning, such as neural networks or evolutionary algorithms.

Searching for solutions to a problem among all possible alternatives is an important capability but one that has not been researched nearly enough due to its complexity. A brute-force search would seem to require enumerating all alternatives, which is impossible even on extremely simple problems, whereas other approaches seem so specialized that they have little value outside their specific domain (and sometimes not even there). In contrast, machine learning methods can be applied to virtually any problem where the solution space is finite (e.g., finding a path through a graph or board games like chess).

The brute-force approach of enumerating all possible combinations has been successfully applied to optimization problems where only a few desirable solutions are available, but there are many applications that require solving very large problems with thousands or millions of potential solutions. Examples include the Traveling Salesman Problem and scheduling tasks for an airline crew using dozens of variables (e.g., number of passengers flying, weight, the distance between origin and destination cities), a task which becomes more difficult because it must deal with occasional breakdowns in equipment. Any feasible algorithm will require shortcuts that often involve approximations or heuristics. Source.

**What is the main purpose of using PCA on a dataset, and what are some examples of its application?**

PCA is short for Principal Component Analysis, and it’s a technique used to reduce the dimensionality of a dataset. In other words, it helps you to find the important Variables in a dataset and get rid of the noise. PCA is used in a variety of fields, from image recognition to facial recognition to machine learning.

PCA has a few main applications: **– Reducing the number of features in a dataset ****– Finding relationships between features ****– Identifying clusters in data ****– Visualizing data**

Let’s take a look at an example. Say you have a dataset with 1000 features (variables). PCA can help you reduce that down to, say, 10 features that explain the majority of variance in the data. This is helpful because it means you can build a model with far fewer features, which makes it simpler and faster. In addition, PCA can help you to find relationships between features and identify clusters in data. All of this can be extremely helpful in understanding and using your data.

**PCA is an important tool in Machine Learning, and has a number of applications.** The main purpose of PCA is to reduce the dimensionality of a dataset, while still retaining as much information as possible. This can be useful when dealing with very large datasets, as it can make training and testing faster and more efficient. PCA is also often used for data visualization, as it can help to create clear and concise visualizations of high-dimensional data. Finally, PCA can be used for feature selection, as it can help to identify the most important features in a dataset. PCA is a powerful tool that can be applied in many different ways, and is an essential part of any Machine Learning workflow.

**What are subservient sounding male names suitable for an automated assistant?**

Artificial intelligence is increasingly becoming a staple in our lives, with everything from our homes to our workplaces being automated to some degree. And as AI becomes more ubiquitous, we are starting to see a trend of subservient-sounding names being given to male automated assistants. This is likely due to a combination of factors, including the fact that women are still primarily seen as domestic servants and the fact that many people find it easier to relate to a male voice. Whatever the reason, it seems that subservient-sounding names are here to stay when it comes to male AI. So if you’re looking for a name for your new automated assistant, here are some subservient-sounding male names to choose from:

– Jasper: A popular name meaning “treasurer” or “bringer of riches.”

– Custer: A name derived from the Latin word for “servant.”

– Luther: A Germanic name meaning “army of warriors.”

– Benson: A name of English origin meaning “son of Ben.”

– Wilfred: A name of Germanic origin meaning “desires peace.”

In recent years, there has been an increasing trend of using subservient sounding male names for automated assistants. Artificial intelligence is becoming more prevalent in our everyday lives, and automation is slowly but surely taking over many routine tasks. As such, it’s no surprise that we’re seeing a name trend emerge that reflects our growing dependence on these technologies. So what are some suitable names for an automated assistant? How about “Robo-Bob”? Or “Mecha-Mike”? Perhaps even “Cyber-Steve”? Whatever you choose, just be sure to pick a name that sounds suitably subservient! After all, your automated assistant should reflect your growing dependency on technology… and not your growing dominance over it!

**How do you calculate user churn rate?**

Churn rate is a metric that measures the percentage of users who leave or discontinue using a service within a given time period. The churn rate is an important metric for businesses to track because it can help them identify areas where their product or service is losing users. There are many ways to calculate the churn rate, but one of the most popular methods is to use machine learning or artificial intelligence. Artificial intelligence can help identify patterns in user behavior that may indicate that someone is about to leave the service. By tracking these patterns, businesses can be proactive in addressing user needs and reducing the chances of losing them. In addition, automation can also help reduce the churn rate by making it easier for users to stay with the service. Automation can handle tasks like customer support and billing, freeing up users’ time and making it less likely that they will discontinue their subscription. By using machine learning and artificial intelligence, businesses can more accurately predict and prevent user churn.

There are a few different ways to calculate the user churn rate using artificial intelligence. One way is to use a technique called **Artificial Neural Networks**. This involves training a computer to recognize patterns in data. Once the computer has learned to recognize these patterns, it can then make predictions about future data. Another way to calculate the user churn rate is to use a technique called **Support Vector Machines**. This approach uses algorithms to find the boundaries between different groups of data. Once these boundaries have been found, the algorithm can then make predictions about new data points. Finally, there is a technique called **Bayesian inference**. This approach uses probability theory to make predictions about future events. **By using these three techniques, it is possible to calculate the user churn rate with a high degree of accuracy.**

**How to confuse Machine Learning and AI?**

**As a machine learning researcher, what are the recent trends in the field that you don’t like?**

Folks with no educational background taking a MOOC or two in deep learning, entering the field, and skipping over basic concepts in machine learning–specificity/sensitivity, the difference between supervised and unsupervised learning, linear regression, ensembles, proper design of a study/test, probability distributions… With enough MOOCs, you can sound like you know what you are doing, but as soon as something goes wrong or changes slightly, there’s no knowledge about how to fix it. Big problem in employment, particularly when hiring a first machine learning engineer/data scientist.. Source: Colleen Farrelly

With rapid developments of artificial intelligence (AI) technology, the use of AI technology to mine clinical data has become a major trend in medical industry. Utilizing advanced AI algorithms for medical image analysis, one of the critical parts of clinical diagnosis and decision-making, has become an active research area both in industry and academia. Recent applications of deep leaning in medical image analysis involve various computer vision-related tasks such as classification, detection, segmentation, and registration. Among them, classification, detection, and segmentation are fundamental and the most widely used tasks that can be done with Scale but the rest of the more demanding methods require a more sophisticated platform for example Tasq.

Although there exist a number of reviews on deep learning methods on medical image analysis, most of them emphasize either on general deep learning techniques or on specific clinical applications. The most comprehensive review paper is the work of Litjens et al. published in 2017. Deep learning is such a quickly evolving research field; numerous state-of-the-art works have been proposed since then.

AI Technologies in Medical Image Analysis

Different medical imaging modalities have their unique characteristics and different responses to human body structure and organ tissue and can be used in different clinical purposes. The commonly used image modalities for diagnostic analysis in clinic include projection imaging (such as X-ray imaging), computed tomography (CT), ultrasound imaging, and magnetic resonance imaging (MRI). MRI sequences include T1, T1-w, T2, T2-w, diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC), and fluid attenuation inversion recovery (FLAIR). Figure 1 demonstrates a few examples of medical image modalities and their corresponding clinical applications.

Image Classification for Medical Image Analysis

As a fundamental task in computer vision, image classification plays an essential role in computer-aided diagnosis. A straightforward use of image classification for medical image analysis is to classify an input image or a series of images as either containing one (or a few) of predefined diseases or free of diseases (i.e., healthy case). Typical clinical applications of image classification tasks include skin disease identification in dermatology, eye disease recognition in ophthalmology (such as diabetic retinopathy, glaucoma, and corneal diseases). Classification of pathological images for various cancers such as breast cancer and brain cancer also belongs to this area.

Convolutional neural network (CNN) is the dominant classification framework for image analysis. With the development of deep learning, the framework of CNN has continuously improved. AlexNet was a pioneer convolutional neural network, which was composed of repeated convolutions, each followed by ReLU and max pooling operation with stride for downsampling. The proposed VGGNet used convolution kernels and maximum pooling to simplify the structure of AlexNet and showed improved performance by simply increasing the number and depth of the network. Via combining and stacking , and convolution kernels and pooling, the inception network and its variants increased the width and the adaptability of the network. ResNet and DenseNet both used skip connections to relieve the gradient vanishing. SENet proposed a squeeze-and-excitation module which enabled the model to pay more attention to the most informative channel features. The family of EfficientNet applied AUTOML and a compound scaling method to uniformly scale the width, depth, and resolution of the network in a principled way, resulting in improved accuracy and efficiency. Source: **Kelly Holland**

**Today, a lot of AI works are using GPU. Why use GPU if the one for processing things is the CPU?**

GPUs also process things. It’s just that they’re better and faster at “specific” things.

The main stuff a GPU is “awesome” at, exactly because it is designed to be specific with those: Matrix maths. The sorts of calculation used when converting a bunch of 3d points (XYZ values) into an approximation of how such a shape would look from a camera. I.e. rendering a 2d picture from a 3d object – exactly why a GPU is made in the first place: https://www.3dgep.com/3d-math-primer-for-game-programmers-matrices/

The sorts of calculations used in current “AI” ? Guess what? Matrix maths:

https://rossbulat.medium.com/ai-essentials-working-with-matrices-2ceb9ca3bd1b

By Irne Barnard

**What is the smallest number of data points usable for reliable machine learning?**

This is perhaps the most important question in computational learning theory. In fact, some of the most important theorems of machine learning like the No Free Lunch Theorem and the Fundamental Theorem of Statistical Learning are aimed at answering this very question.

Formally, the smallest number of data points needed for successfully learning a classification rule using a machine learning (ML) algorithm is called the sample complexity of the algorithm. Now, you might wonder why sample complexity is such a big deal. It’s because sample complexity is to ML algorithms what computational complexity is to any algorithm. It measures the minimum amount of resource (i.e. the data) that is required to achieve the desired goal.

There are several interesting answers to the question of sample complexity, that arise from various assumptions on the learner. In what follows, I will give the answer under some popular assumptions/scenarios.

Scenario 1: **Perfect Learning**

In our first scenario, we consider the problem of learning the correct hypothesis (classification rule) amongst a set of plausible hypotheses. The data is sampled independently from an unknown probability distribution.

It turns out that under no further assumptions on the data-generating probability distribution, the problem is impossible. In other words, there is no algorithm that can learn the correct classification rule perfectly from any finite amount of data. This result is called the No Free Lunch Theorem in machine learning. I’ve discuss this result in more detail here.

Scenario 2: **Probably Approximately Correct (PAC) Learning**

For the second scenario, we consider the problem of learning the correct hypothesis approximately, with high probability. That is, our algorithm may fail to identify even an approximately correct hypothesis with some small probability. This relaxation allows us to give a slightly more useful answer to the question.

The answer to this question is of the order of the VC-dimension of the hypothesis class. More precisely, if we want the algorithm to be approximately correct with an error of at most ϵϵ with a probability of at least 1−δ1−δ, then we need a minimum of dϵlog(1ϵδ)dϵlog(1ϵδ), where dd is the VC-dimension of the hypothesis class. Note that dd can be infinite for certain hypothesis classes. In that case, it is not possible to succeed in the learning task even approximately, even with high probability. On the other hand, if dd is finite, we say that the hypothesis class is (ϵ,δ)−(ϵ,δ)−PAC learnable. (I explain PAC-learnability in more detail in this answer.)

**Scenario 3**: **Learning with a Teacher**

In the previous two scenarios, we assume that the data that is presented to the learner is randomly sampled from an unknown probability distribution. For this scenario, we do away with the randomness. Instead, we assume that the learner is presented with a carefully chosen set of training data points that are picked by a benevolent teacher. (By benevolent teacher, I mean that the teacher tries to make the learner guess the correct hypothesis with the fewest number of data points.)

In this case, the answer to the question is the teaching dimension. It is interesting to note that there is no straightforward relation between the teaching dimension and VC-dimension of a hypothesis class. They can be arbitrarily far from each other. (If you’re curious to know the relation between the two, here is a nice paper.)

In addition to these, there are other notions of “dimension” that characterize the sample complexity of a learning task under different scenarios. For example, there is the Littlestone dimension for online learning and Natarajan dimension for multi-class learning. Intuitively, these dimensions capture the inherent hardness of a machine learning task. The harder the task, the higher the dimension and the corresponding sample complexity.

To those of you seeking for exact numbers, here’s a note I added in the comments section: I wish I could add some useful empirical results, but the sample complexity bounds obtained by the PAC-learning approach are really loose to the point of being useless in case of most state-of-the-art ML algorithms like deep learning. So, the results I presented are basically a theoretical curiosity at this point. However, this might change in the near future as lots of researchers are working on strengthening this framework.

Source: Muni Sreenivas Pydi

**How can a machine learning algorithm learn from small datasets?**

As mentioned in the other answer, this can be understood using the concept of bias-variance tradeoff.

For any machine learning model, want to find a function that approximately fits your data. So, you essentially define the following:

- Class of functions : Instead of searching in the space of all possible functions, you restrict the space of functions that the algorithm searches over. For example, a linear classifier will search among all possible lines, but will not consider more complex curves.
- Loss function : This is used to compare two functions from the above class of functions. For instance, in SVM, you would prefer line 1 to line 2 if line 1 has a larger margin than line 2.

Now, the simpler your class of functions is, the smaller the amount of data required. To get some intuition for this, think about a regression problem that has three features. So, a linear function class will have the following form:

y=a0+a1x1+a2x2+a3x3y=a0+a1x1+a2x2+a3x3

Every point (p, q, r, s) in the 4-dimensional space corresponds to a function of the above form, namely y=p+qx1+rx2+sx3y=p+qx1+rx2+sx3. So, you need to find one point in that 4D space that fits your data well.

Now, if instead of the class of linear functions, you chose quadratic functions, your functions would be of the following form:

y=a0+a1x1+a2x2+ a3x3+a4x1x2+ a5x2x3+a6x1x3+ a7x21+a8x22+a9x23y = a0+a1x1+a2x2+a3x3 + a4x1x2+a5x2x3+a6x1x3+a7x12+a8x22+a9x32

So now, you have to search for the best point in a 10D space! Therefore, you need more data to distinguish these larger number of points from each other.

With that intuition, we can say that to learn from small amount of data, you want to define a small enough function class.

Note: While in the above example, we simply look at the no. of parameters to get a sense of complexity of the function class, in general, more parameters does not necessarily mean more complexity [for instance, if a lot of the parameters are strongly correlated].

Source: Prasoon Goyal

**Best Machine Learning Books That All Data Scientists Must Read.**

**1. Artificial Intelligence: A Modern Approach**

#### Experts Opinions

I like this book very much. When in doubt I look there, and usually find what I am looking for, or I find references on where to go to study the problem more in depth. I like that it tries to show how various topics are interrelated, and to give general architectures for general problems … It is a jump in quality with respect to the AI books that were previously available. *— Prof. Giorgio Ingargiola (Temple)*.

Really excellent on the whole and it makes teaching AI a lot easier. *— Prof. Ram Nevatia (USC)*.

It is an impressive book, which begins just the way I want to teach, with a discussion of agents, and ties all the topics together in a beautiful way. *— Prof. George Bekey (USC)*. Buy it now

2. **Deep Learning (Adaptive Computation and Machine Learning series)**

**Experts Opinions**

“Written by three experts in the field, *Deep Learning* is the only comprehensive book on the subject.” —Elon Musk, cochair of OpenAI; cofounder and CEO of Tesla and SpaceX.

“If you want to know here deep learning came from, what it is good for, and where it is going, read this book.” —Geoffrey Hinton FRS, Professor, University of Toronto, Research Scientist at Google. Buy it

**Experts Opinions**

“An exceptional resource to study Machine Learning. You will find clear-minded, intuitive explanations, and a wealth of practical tips.” —François Chollet, Author of Keras, author of Deep Learning with Python.

“This book is a great introduction to the theory and practice of solving problems with neural networks; I recommend it to anyone interested in learning about practical ML.” — Peter Warden, Mobile Lead for TensorFlow. Buy it.

#### 4. Python Machine Learning – Second Edition: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2nd Edition

**When should you not normalize data in machine learning?**

First things first, I don’t think there are many questions of the form “Is it a good practice to always X in machine learning” where the answer is going to be definitive. Always? Always always? Across parametric, non-parametric, Bayesian, Monte Carlo, social science, purely mathematic, and million feature models? That’d be nice, wouldn’t it! Anyway feel free to check out this interactive demo from deepchecks.

Concretely though, here are a few ways in which: it just depends.

Some times when normalizing is good:

1) Several algorithms, in particular SVMs come to mind, can sometimes converge far faster on normalized data (although why, precisely, I can’t recall).

2) When your model is sensitive to magnitude, and the units of two different features are different, and arbitrary. This is like the case you suggest, in which something gets more influence than it should.

But of course — not all algorithms are sensitive to magnitude in the way you suggest. Linear regression coefficients will be identical if you do, or don’t, scale your data, because it’s looking at proportional relationships between them.

Some times when normalizing is bad:

1) When you want to interpret your coefficients, and they don’t normalize well. Regression on something like dollars gives you a meaningful outcome. Regression on proportion-of-maximum-dollars-in-sample might not.

2) When, in fact, the units on your features are meaningful, and distance does make a difference! Back to SVMs — if you’re trying to find a max-margin classifier, then the units that go into that ‘max’ matter. Scaling features for clustering algorithms can substantially change the outcome. Imagine four clusters around the origin, each one in a different quadrant, all nicely scaled. Now, imagine the y-axis being stretched to ten times the length of the the x-axis. instead of four little quadrant-clusters, you’re going to get the long squashed baguette of data chopped into four pieces along its length! (And, the important part is, you might prefer either of these!)

In I’m sure unsatisfying summary, the most general answer is that you need to ask yourself seriously what makes sense with the data, and model, you’re using. Source: ABC of Data Science and ML

**How do you prepare data for XGBoost?**

Data preparation is a critical step in the data science process, and it is especially important when working with XGBoost. XGBoost is a powerful machine learning algorithm that can provide accurate predictions on data sets of all sizes. However, in order to get the most out of XGBoost, it is important to prepare the data in a way that is conducive to machine learning. This means ensuring that the data is clean, feature engineering has been performed, and that the data is in a format that can be easily consumed by the algorithm. By taking the time to prepare the data properly, data scientists can significantly improve the performance of their machine learning models.

**When preparing the dataset for your machine learning model, you should use one-hot encoding on what type of data?**

In machine learning and data science, one-hot encoding is a process by which categorical data is converted into a format that is suitable for use with machine learning algorithms. The categorical data is first grouped by type, and then a binary value is assigned to each group. This binary value corresponds to the group’s position in the encoding scheme. For example, if there are three groups, the first group would be assigned a value of ‘0’, the second group would be assigned a value of ‘1’, and the third group would be assigned a value of ‘2’. One-hot encoding is often used when working with categorical data, as it can help to improve the performance of machine learning models. In addition, one-hot encoding can also make it easier to visualize the relationship between different categories.

In machine learning and data science, one-hot encoding is a method used to convert categorical features into numerical features. This is often necessary when working with machine learning models, as many models can only accept numerical input. However, one-hot encoding is not without its problems. The most significant issue is the potential for increased dimensionality – if a dataset has too many features, it can be difficult for the model to learn from the data. In addition, one-hot encoding can create sparse datasets, which can also be difficult for some machine learning models to handle. Despite these issues, one-hot encoding remains a popular method for preparing data for machine learning models.

** A retail company wants to start personalizing product recommendations to visitors of their website. They have historical data of what products the users have purchased and want to implement the system for new users, prior to them purchasing a product. What’s one way of phrasing a machine learning problem for this situation?**

For this retail company, a machine learning problem could be phrased as a prediction problem. The goal would be to build a model that can take in data about a new user (such as demographic information and web browsing history) and predict which products they are likely to purchase. This would allow the company to give each new user personalized product recommendations, increasing the chances of making a sale. Data science techniques such as feature engineering and model selection would be used to build the best possible prediction model. By phrasing the machine learning problem in this way, the retail company can make the most of their historical data and improve the user experience on their website.

There are many ways to frame a machine learning problem for a retail company that wants to start personalizing product recommendations to visitors of their website. One way is to focus on prediction: using historical data of what products users have purchased, can we predict which products new users will be interested in? This is a task that machine learning is well suited for, and with enough data, we can build a model that accurately predicts product interests for new users. Another way to frame the problem is in terms of classification: given data on past purchases, can we classify new users into groups based on their product interests? This would allow the retail company to more effectively target personalization efforts. There are many other ways to frame the machine learning problem, depending on the specific goals of the company. But no matter how it’s framed, machine learning can be a powerful tool for personalizing product recommendations.

** A data scientist is trying to determine how a model is doing based on training evaluation. The train accuracy plateaus out at around 70% and the validation accuracy is 67%. How should the data scientist interpret these results?**

When working with machine learning models, it is important to evaluate how well the model is performing. This can be done by looking at the train and validation accuracy. In this case, the train accuracy has plateaued at around 70% and the validation accuracy is 67%. There are a few possible explanations for this. One possibility is that the model is overfitting on the training data. This means that the model is able to accurately predict labels for the training data, but it is not as effective at generalizing to new data. Another possibility is that there is a difference in the distribution of the training and validation data. If the validation data is different from the training data, then it makes sense that the model would have a lower accuracy on the validation data. To determine which of these explanations is most likely, the data scientist should look at the confusion matrix and compare the results of the training and validation sets. If there are large differences between the two sets, then it is likely that either overfitting or a difference in distributions is to blame. However, if there isn’t a large difference between the sets, then it’s possible that 70% is simply the best accuracy that can be achieved given the data.

One important consideration in machine learning is how well a model is performing. This can be determined in a number of ways, but one common method is to split the data into a training set and a validation set. The model is then trained on the training data and evaluated on the validation data. If the model is performing well, we would expect to see a similar accuracy on both the training and validation sets. However, in this case the training accuracy plateaus out at around 70% while the validation accuracy is only 67%. This could be indicative of overfitting, where the model has fit the training data too closely and does not generalize well to new data. In this case, the data scientist should look for ways to improve the model so that it performs better on the validation set.

**When updating your weights using the loss function, what dictates how much change the weights should have?**

In machine learning and data science, the learning rate is a parameter that dictates how much change the weights should have when updating them using the loss function. The learning rate is typically a small value between 0 and 1. A higher learning rate means that the weights are updated more quickly, which can lead to faster convergence but can also lead to instability. A lower learning rate means that the weights are updated more slowly, which can lead to slower convergence but can also help avoid overfitting. The optimal learning rate for a given problem can be found through trial and error. The bias term is another parameter that can affect the weight updates. The bias term is used to prevent overfitting by penalizing models that make too many assumptions about the data. The initial weights are also important, as they determine where the model starts on the optimization landscape. The batch size is another important parameter, as it defines how many training examples are used in each iteration of weight updates. A larger batch size can lead to faster convergence, but a smaller batch size can help avoid overfitting. Finding the optimal values for all of these parameters can be a challenge, but doing so is essential for training high-quality machine learning models.

**An ad tech company is using an XGBoost model to classify its clickstream data. The company’s Data Scientist is asked to explain how the model works to a group of non-technical colleagues. What is a simple explanation the Data Scientist can provide?**

Machine learning is a form of artificial intelligence that allows computers to learn from data, without being explicitly programmed. machine learning is a powerful tool for solving complex problems, and XGBoost is a popular machine learning algorithm. machine learning algorithms like XGBoost work by building a model based on training data, and then using that model to make predictions on new data. In the case of the ad tech company, the Data Scientist has used XGBoost to build a model that can classify clickstream data. This means that the model can look at new data and predict which category it belongs to. For example, the model might be able to predict whether a user is likely to click on an ad or not. The Data Scientist can explain how the model works by showing how it makes predictions on new data.

Machine learning is a method of teaching computers to learn from data, without being explicitly programmed. machine learning is a subset of artificial intelligence (AI). The XGBoost algorithm is a machine learning technique used to create models that predict outcomes by learning from past data. XGBoost is an implementation of gradient boosting, which is a machine learning technique for creating models that make predictions by combining the predictions of multiple individual models. The XGBoost algorithm is highly effective and is used by many organizations, including ad tech companies, to classify their data. The Data Scientist can explain how the XGBoost model works by providing a simple explanation of machine learning and how the XGBoost algorithm works. machine learning is a method of teaching computers to learn from data, without being explicitly programmed.

**An ML Engineer at a real estate startup wants to use a new quantitative feature for an existing ML model that predicts housing prices. Before adding the feature to the cleaned dataset, the Engineer wants to visualize the feature in order to check for outliers and overall distribution and skewness of the feature. What visualization technique should the ML Engineer use? **

The machine learning engineer at the real estate startup should use a visualization technique in order to check for outliers and overall distribution and skewness of the new quantitative feature. There are many different visualization techniques that could be used for this purpose, but two of the most effective are histograms and scatterplots. A histogram can show the distribution of values for the new feature, while a scatterplot can help to identify any outliers. By visualizing the data, the engineer will be able to ensure that the new feature is of high quality and will not impact the performance of the machine learning model.

**When updating your weights using the loss function, what dictates how much change the weights should have?**

In machine learning and data science, the learning rate is a parameter that dictates how much change the weights should have when updating them using the loss function. The learning rate is typically a small value between 0 and 1. A higher learning rate means that the weights are updated more quickly, which can lead to faster convergence but can also lead to instability. A lower learning rate means that the weights are updated more slowly, which can lead to slower convergence but can also help avoid overfitting. The optimal learning rate for a given problem can be found through trial and error. The bias term is another parameter that can affect the weight updates. The bias term is used to prevent overfitting by penalizing models that make too many assumptions about the data. The initial weights are also important, as they determine where the model starts on the optimization landscape. The batch size is another important parameter, as it defines how many training examples are used in each iteration of weight updates. A larger batch size can lead to faster convergence, but a smaller batch size can help avoid overfitting. Finding the optimal values for all of these parameters can be a challenge, but doing so is essential for training high-quality machine learning models.

The loss function is a key component of machine learning algorithms, as it determines how well the model is performing. When updating the weights using the loss function, the learning rate dictates how much change the weights should have. The learning rate is a hyperparameter that can be tuned to find the optimal value for the model. The bias term is another important factor that can influence the weights. The initial weights can also play a role in how much change the weights should have. The batch size is another important factor to consider when updating the weights using the loss function.

**A data scientist wants to clean and merge two small datasets stored in CSV format. What tool can they use to merge these datasets together?**

As a data scientist, you often need to work with multiple datasets in order to glean insights that would be hidden in any one dataset on its own. In order to do this, you need to be able to clean and merge datasets quickly and efficiently. One tool that can help you with this task is Pandas. Pandas is a Python library that is specifically designed for data analysis. It offers a wide range of features that make it well-suited for merging datasets, including the ability to read in CSV format, clean data, and merge datasets with ease. In addition, Pandas integrates well with other machine learning libraries such as Scikit-learn, making it a valuable tool for data scientists.

As a data scientist, one of the most important skills is knowing how to clean and merge datasets. This can be a tedious and time-consuming process, but it is essential for machine learning and data science projects. There are several tools that data scientists can use to merge datasets, but one of the most popular options is pandas. Pandas is a Python library that offers a wide range of functions for data manipulation and analysis. Additionally, pandas has built-in support for reading and writing CSV files. This makes it an ideal tool for merging small datasets stored in CSV format. With pandas, data scientists can quickly and easily clean and merge their data, giving them more time to focus on other aspects of their projects.

** A real estate company is building a linear regression model to predict housing prices for different cities in the US. Which of the following is NOT a good metric to measure performance of their regression model?**

Machine learning is a subset of data science that deals with the design and development of algorithms that can learn from and make predictions on data. Linear regression is a machine learning algorithm used to predict numerical values based on a linear relationship between input variables. When building a linear regression model, it is important to choose an appropriate metric to measure the performance of the model. The F1 score, R-squared value, and mean-squared error are all valid metrics for measuring the performance of a linear regression model. However, the mean absolute error is not a good metric to use for this purpose, as it does not take into account the direction of the prediction error (i.e., whether the predicted value is higher or lower than the actual value). As such, using the mean absolute error as a metric for evaluating the performance of a linear regression model could lead to inaccurate results.

**A real estate company wants to provide its customers with a more accurate prediction of the final sale price for houses they are considering in various cities. To do this, the company wants to use a fully connected neural network trained on data from the previous ten years of home sales, as well as other features. What kind of machine learning problem does this situation most likely represent?**

Answer: Regression

**Which feature of Amazon SageMaker can you use for preprocessing the data?**

Answer: **Amazon Sagemaker Notebook instances**

Amazon SageMaker enables developers and data scientists to build, train, tune, and deploy machine learning (ML) models at scale. You can deploy trained ML models for real-time or batch predictions on unseen data, a process known as *inference*. However, in most cases, the raw input data must be preprocessed and can’t be used directly for making predictions. This is because most ML models expect the data in a predefined format, so the raw data needs to be first cleaned and formatted in order for the ML model to process the data. You can use the Amazon SageMaker built-in Scikit-learn library for preprocessing input data and then use the Amazon SageMaker built-in Linear Learner algorithm for predictions.

**What setting, when creating an Amazon SageMaker notebook instance, can you use to install libraries and import data?**

Answer: **LifeCycle Configuration**

**You work for the largest coffee chain in the world. You’ve recently decided to source beans from a new market to create new blends and flavors. These beans come from 30 different growers, in 3 different countries. In order to keep a consistent flavor, you have each grower send samples of their beans to your tasting baristas who rate the beans on 20 different dimensions. You now need to group the beans together so the supply can be diversified yet the flavor of the final product kept as consistent as possible.**

**What is one way you could convert this business situation into a machine learning problem?**

Answer:** **

**In which phase of the ML pipeline does the machine learn from the data?**

Answer: **Model Training**

**A text analytics company is developing a text classification model to detect whether a document involves offensive content or not. The training dataset included ten non-offensive documents for every one offensive document. Their model resulted in an accuracy score of 94%.**

**What can we conclude from this result?**

Answer: **Accuracy is the wrong metric here, because it can be heavily influenced by the large class (non-offensive documents).**

**A Machine Learning Engineer is creating a regression model for forecasting company revenue based on an internal dataset made up of past sales and other related data.**

**What metric should the Engineer use to evaluate the ML model?**

**Root Mean Squared error (RMSE)**

**the standard deviation of the residuals (prediction errors)**. Residuals are a measure of how far from the regression line data points are; RMSE is a measure of how spread out these residuals are. In other words, it tells you how concentrated the data is around the line of best fit.

**An ML scientist has built a decision tree model using scikit-learn with 1,000 trees. The training accuracy for the model was 99.2% and the test accuracy was 70.3%. Should the Scientist use this model in production?**

**No, because it is not generalizing well on the test set**

**The curse of dimensionality relates to which of the following?**

**The curse of dimensionality relates to a**** high number of features in a dataset.**

Curse of Dimensionality **describes the explosive nature of increasing data dimensions and its resulting exponential increase in computational efforts required for its processing and/or analysis**. This term was first introduced by Richard E.

**A Data Scientist wants to include “month” as a categorical column in a training dataset for an ML model that is being built. However, the ML algorithm gives an error when the column is added to the training data. What should the Data Scientist do to add this column?**

Answer:

**StandardScaler** standardizes a feature by subtracting the mean and then scaling to unit variance. Unit variance means dividing all the values by the standard deviation. StandardScaler does not meet the strict definition of scale I introduced earlier.

**What is the primary reason that one might want to pick either random search or Bayesian optimization over grid search when performing hyperparameter optimization?**

**Random search and Bayesian methods leave smaller unexplored regions than grid searches**

**A Data Scientist trained an XGBoost model to classify internal documents for further inquiry, and now wants to evaluate the model’s performance by looking at the results visually. What technique should the Data Scientist use in this situation?**

**Machine Learning Pipeline Goals**

**Common Machine Learning Use Cases**

**What is a machine learning model?**

**What are features and weights meaning in Machine Learning?**

Reference: Wiki

**PRE-PROCESSING AND FEATURE ENGINEERING**

**Source**: https://github.com/mortezakiadi/ML-Pipeline/wiki

**How to Choose the right Sagemaker built-in algorithm?**

This is a general guide for choosing which algorithm to use depending on what business problem you have and what data you have.

**Machine Learning Deployment and Monitoring**

**Machine Learning Model Performance Evaluation Metrics**

**Machine Learning Breaking News and Top Stories**

- Enhancing LLM collaboration for smarter, more efficient solutionsby Alex Shipps | MIT CSAIL (MIT News - Machine learning) on September 16, 2024 at 8:30 pm
“Co-LLM” algorithm helps a general-purpose AI model collaborate with an expert large language model by combining the best parts of both answers, leading to more factual responses.

- A fast and flexible approach to help doctors annotate medical scansby Alex Shipps | MIT CSAIL (MIT News - Machine learning) on September 9, 2024 at 8:25 pm
“ScribblePrompt” is an interactive AI framework that can efficiently highlight anatomical structures across different medical scans, assisting medical workers to delineate regions of interest and abnormalities.

- Study: Transparency is often lacking in datasets used to train large language modelsby Adam Zewe | MIT News (MIT News - Machine learning) on August 30, 2024 at 9:00 am
Researchers developed an easy-to-use tool that enables an AI practitioner to find data that suits the purpose of their model, which could improve accuracy and reduce bias.

- First AI + Education Summit is an international push for “AI fluency”by Andrew Whitacre | RAISE Initiative (MIT News - Machine learning) on August 27, 2024 at 8:30 am
The three-day, hands-on conference hosted by the MIT RAISE Initiative welcomed youths and adults from nearly 30 countries.

- 3 Questions: How to prove humanity onlineby Adam Zewe | MIT News (MIT News - Machine learning) on August 16, 2024 at 4:00 am
AI agents could soon become indistinguishable from humans online. Could “personhood credentials” protect people against digital imposters?

- New open-source tool helps to detangle the brainby Anne McGovern | MIT Lincoln Laboratory (MIT News - Machine learning) on August 14, 2024 at 6:30 pm
The software tool NeuroTrALE is designed to quickly and efficiently process large amounts of brain imaging data semi-automatically.

- LLMs develop their own understanding of reality as their language abilities improveby Alex Shipps | MIT CSAIL (MIT News - Machine learning) on August 14, 2024 at 5:20 pm
In controlled experiments, MIT CSAIL researchers discover simulations of reality developing deep within LLMs, indicating an understanding of language beyond simple mimicry.

- MIT researchers use large language models to flag problems in complex systemsby Adam Zewe | MIT News (MIT News - Machine learning) on August 14, 2024 at 4:00 am
The approach can detect anomalies in data recorded over time, without the need for any training.

- Helping robots practice skills independently to adapt to unfamiliar environmentsby Alex Shipps | MIT CSAIL (MIT News - Machine learning) on August 8, 2024 at 2:45 pm
A new algorithm helps robots practice skills like sweeping and placing objects, potentially helping them improve at important tasks in houses, hospitals, and factories.

- Precision home robots learn with real-to-sim-to-realby Rachel Gordon | MIT CSAIL (MIT News - Machine learning) on July 31, 2024 at 7:45 pm
CSAIL researchers introduce a novel approach allowing robots to be trained in simulations of scanned home environments, paving the way for customized household automation accessible to anyone.

- Method prevents an AI model from being overconfident about wrong answersby Adam Zewe | MIT News (MIT News - Machine learning) on July 31, 2024 at 4:00 am
More efficient than other approaches, the “Thermometer” technique could help someone know when they should trust a large language model.

- Study: When allocating scarce resources with AI, randomization can improve fairnessby Adam Zewe | MIT News (MIT News - Machine learning) on July 24, 2024 at 4:00 am
Introducing structured randomization into decisions based on machine-learning model predictions can address inherent uncertainties while maintaining efficiency.

- MIT researchers advance automated interpretability in AI modelsby Rachel Gordon | MIT CSAIL (MIT News - Machine learning) on July 23, 2024 at 8:00 pm
MAIA is a multimodal agent that can iteratively design experiments to better understand various components of AI systems.

- Proton-conducting materials could enable new green energy technologiesby David L. Chandler | MIT News (MIT News - Machine learning) on July 23, 2024 at 2:30 pm
Analysis and materials identified by MIT engineers could lead to more energy-efficient fuel cells, electrolyzers, batteries, or computing devices.

- Large language models don’t behave like people, even though we may expect them toby Adam Zewe | MIT News (MIT News - Machine learning) on July 23, 2024 at 4:00 am
A new study shows someone’s beliefs about an LLM play a significant role in the model’s performance and are important for how it is deployed.

- AI model identifies certain breast tumor stages likely to progress to invasive cancerby Adam Zewe | MIT News (MIT News - Machine learning) on July 22, 2024 at 6:00 pm
The model could help clinicians assess breast cancer stage and ultimately help in reducing overtreatment.

- Machine learning unlocks secrets to advanced alloysby Poornima Apte | Department of Materials Science and Engineering (MIT News - Machine learning) on July 18, 2024 at 6:55 pm
An MIT team uses computer models to measure atomic patterns in metals, essential for designing custom materials for use in aerospace, biomedicine, electronics, and more.

- Creating and verifying stable AI-controlled systems in a rigorous and flexible wayby Alex Shipps | MIT CSAIL (MIT News - Machine learning) on July 18, 2024 at 1:20 am
Neural network controllers provide complex robots with stability guarantees, paving the way for the safer deployment of autonomous vehicles and industrial machines.

- AI method radically speeds predictions of materials’ thermal propertiesby Adam Zewe | MIT News (MIT News - Machine learning) on July 16, 2024 at 8:55 pm
The approach could help engineers design more efficient energy-conversion systems and faster microelectronic devices, reducing waste heat.

- How to assess a general-purpose AI model’s reliability before it’s deployedby Adam Zewe | MIT News (MIT News - Machine learning) on July 16, 2024 at 4:00 am
A new technique enables users to compare several large models and choose the one that works best for their task.

**How do you export data from BigQuery to a CSV file?**

Google Cloud’s BigQuery is a powerful tool for storing and querying large data sets. However, sometimes you may need to export data from BigQuery in order to perform additional analysis or simply to have a backup. Thankfully, Google Cloud makes it easy to export data from BigQuery to a CSV file.

- The first step is to select the dataset that you want to export.
- Next, click on the “Export Table” button. In the pop-up window, select “CSV” as the file format and choose a location to save the file.
- Finally, click on the “Export” button and Google Cloud will begin exporting the data.
- Depending on the size of the data set, this may take several minutes. Once the export is complete, you will have a CSV file containing all of the data from BigQuery.

**Alternatively, Simply run the following command: **

“bq extract –destination_format=CSV [dataset_name] [table_name]”.

This will export your data to a CSV file in Google Cloud Storage. You can then download the file from Google Cloud Storage and use it in another program. Alternatively, you can use the “bq load” command to load your data directly into another Google Cloud service, such as Google Sheets.

**What is the Difference Between Mini-Batch and Full-Batch in Machine Learning?**

In the field of machine learning, there are two types of batch sizes that are commonly used: mini-batch and full-batch. Both have their pros and cons, and the choice of which to use depends on the situation. Here’s a quick rundown of the differences between mini-batch and full-batch in machine learning.

**Mini-Batch Machine Learning**

Mini-batch machine learning is a type of batch processing where the data is divided into small batches before being fed into the machine learning algorithm. The advantage of mini-batch machine learning is that it can provide more accurate results than full-batch machine learning, since the data is less likely to be affected by outliers. However, the disadvantage of mini-batch machine learning is that it can be slower than full-batch machine learning, since each batch has to be processed separately.

**Full-Batch Machine Learning**

Full-batch machine learning is a type of batch processing where the entire dataset is fed into the machine learning algorithm at once. The advantage of full-batch machine learning is that it is faster than mini-batch machine learning, since all the data can be processed simultaneously. However, the disadvantage of full-batch machine learning is that it can be less accurate than mini-batch machine learning, since outliers in the dataset can have a greater impact on the results.

So, which should you use? It depends on your needs. If accuracy is more important than speed, then mini-batch machine learning is the way to go. On the other hand, if speed is more important than accuracy, then full-batch machine learning is the way to go.

**The Difference Between Mini-Batch and Full-Batch Learning**

In machine learning, there are two main types of batch learning: mini-batch and full-batch. Both types of batch learning algorithms have their own pros and cons that data scientists should be aware of. In this blog post, we’ll take a look at the difference between mini-batch and full-batch learning so you can make an informed decision about which type of algorithm is right for your project.

Mini-batch learning is a type of batch learning that operates on small subsets of the training data, typically referred to as mini-batches. The advantage of mini-batch learning is that it can be parallelized across multiple processors or devices, which makes training much faster than full-batch training. Another advantage is that mini-batches can be generated on the fly from a larger dataset, which is especially helpful if the entire dataset doesn’t fit into memory. However, one downside of mini-batch learning is that it can sometimes lead to suboptimal results due to its stochastic nature.

**Full-Batch Learning**

Full-batch learning is a type of batch learning that operates on the entire training dataset at once. The advantage of full-batch learning is that it converges to the global optimum more quickly than mini-batch or stochastic gradient descent (SGD) methods. However, the disadvantage of full-batch learning is that it is very slow and doesn’t scale well to large datasets. Additionally, full-batch methods can’t be parallelized across multiple processors or devices due to their sequential nature.

So, which type of batch learning algorithm is right for your project? If you’re working with a small dataset, then full-batch learning might be your best bet. However, if you’re working with a large dataset or need to train your model quickly, then mini=batch or SGD might be better suited for your needs. As always, it’s important to experiment with different algorithms and tuning parameters to see what works best for your particular problem.

**2023 AWS Certified Machine Learning Specialty (MLS-C01) Practice Exams**

Welcome to AWS Certification Machine Learning Specialty (MLS-C01) Practice Exams!

This book is designed to help you prepare for the AWS Certified Machine Learning – Specialty (MLS-C01) exam and earn your AWS certification. The AWS Certified Machine Learning – Specialty (MLS-C01) exam is designed for individuals who have a strong understanding of machine learning concepts and techniques, and who can design, build, and deploy machine learning models on the AWS platform.

In this book, you will find a series of practice exams that are designed to mimic the format and content of the actual MLS-C01 exam. Each practice exam includes a set of multiple choice and multiple response questions that cover a range of topics, including machine learning concepts, techniques, and algorithms, as well as the AWS services and tools used to build and deploy machine learning models.

By working through these practice exams, you can test your knowledge, identify areas where you need further study, and gain confidence in your ability to pass the MLS-C01 exam. Whether you are a machine learning professional looking to earn your AWS certification or a student preparing for a career in machine learning, this book is an essential resource for your exam preparation.

**What is the best Japanese natural language processing (NLP) library?**

NLP is a field of computer science and artificial intelligence that deals with the interactions between computers and human languages. NLP algorithms are used to process and analyze large amounts of natural language data. Japanese NLP libraries are used to develop applications that can understand and respond to Japanese text.

**The best Japanese NLP library depends on your application’s needs. **

For example, if you are developing a machine translation application, you will need a library that supports word sense disambiguation and part-of-speech tagging. If you are developing a chatbot, you will need a library that supports sentence analysis and dialogue management. In general, Japanese NLP libraries can be divided into three categories: rule-based systems, statistical systems, and hybrid systems.

Rule-based systems rely on linguistic rules to process language data.

Statistical systems use statistical models to process language data.

Hybrid systems use a combination of linguistic rules and statistical models to process language data.

**The best Japanese NLP library for your application will depend on the type of NLP tasks you need to perform and your resources (e.g., time, data, computing power).**

## XGBoost is a powerful tool that has a wide range of applications in the real world. XGBoost is a machine learning algorithm that is used to improve the performance of other machine learning algorithms.

## XGBoost has been used to improve the performance of data science models in a variety of fields, including healthcare, finance, and retail.

## In healthcare, **XGBoost has been used to predict patient outcomes, such as length of stay in the hospital and mortality rates**.

## In finance, XGBoost has been used to **predict stock prices and credit card fraud**.

## In retail, XGBoost has been used to** improve customer segmentation and product recommendations. **

## XGBoost is a versatile tool that can be used to improve the performance of machine learning models in many different fields.

Machine Learning For Dummies on iOs: https://apps.apple.com/

Machine Learning For Dummies on Windows: https://www.

Machine Learning For Dummies Web/Android on Amazon: https://www.amazon.

Can AI predicts the tournament winner and golden booth for the FIFA World Cup Football Soccer 2022 in Qatar?

What are some ways we can use machine learning and artificial intelligence for algorithmic trading in the stock market?

How do we know that the Top 3 Voice Recognition Devices like Siri Alexa and Ok Google are not spying on us?

What are some good datasets for Data Science and Machine Learning?

What are popular hobbies among Software Engineers?