Featurepreneur

Search…

ML Interview Questions

Question Set 1

Machine Learning Interview Questions: 4 Categories

We’ve traditionally seen machine learning interview questions pop up in several categories.

1.

The first really has to do with the **algorithms and theory** behind machine learning. You’ll have to show an understanding of how algorithms compare with one another and how to measure their efficacy and accuracy in the right way.

2.

The second category has to do with your **programming skills** and your ability to execute on top of those algorithms and the theory.

3.

The third has to do with your **general interest in machine learning**. You’ll be asked about what’s going on in the industry and how you keep up with the latest machine learning trends.

4.

Finally, there are **company or industry-specific questions** that test your ability to take your general machine learning knowledge and turn it into actionable points to drive the bottom line forward.

We’ve divided this guide to machine learning interview questions into the categories we mentioned above so that you can more easily get to the information you need when it comes to machine learning interview questions.

Machine Learning Interview Questions: Algorithms/Theory

These algorithms questions will test your grasp of the theory behind machine learning.

Variance is error due to too much complexity in the learning algorithm you’re using. This leads to the algorithm being highly sensitive to high degrees of variation in your training data, which can lead your model to overfit the data. You’ll be carrying too much noise from your training data for your model to be very useful for your test data.

The bias-variance decomposition essentially decomposes the learning error from any algorithm by adding the bias, the variance and a bit of irreducible error due to noise in the underlying dataset. Essentially, if you make the model more complex and add more variables, you’ll lose bias but gain some variance — in order to get the optimally reduced amount of error, you’ll have to tradeoff bias and variance. You don’t want either high bias or high variance in your model.

The critical difference here is that KNN needs labeled points and is thus supervised learning, while k-means doesn’t—and is thus unsupervised learning.

Mathematically, it’s expressed as the true positive rate of a condition sample divided by the sum of the false positive rate of the population and the true positive rate of a condition. Say you had a 60% chance of actually having the flu after a flu test, but out of people who had the flu, the test will be false 50% of the time, and the overall population only has a 5% chance of having the flu. Would you actually have a 60% chance of having the flu after having a positive test?

Bayes’ Theorem says no. It says that you have a (.6 * 0.05) (True Positive Rate of a Condition Sample) / (.6*0.05)(True Positive Rate of a Condition Sample) + (.5*0.95) (False Positive Rate of a Population) = 0.0594 or 5.94% chance of getting a flu.

Bayes’ Theorem is the basis behind a branch of machine learning that most notably includes the Naive Bayes classifier. That’s something important to consider when you’re faced with machine learning interview questions.

As a Quora commenter put it whimsically, a Naive Bayes classifier that figured out that you liked pickles and ice cream would probably naively recommend you a pickle ice cream.

Type I error is a false positive, while Type II error is a false negative. Briefly stated, Type I error means claiming something has happened when it hasn’t, while Type II error means that you claim nothing is happening when in fact something is.

A clever way to think about this is to think of Type I error as telling a man he is pregnant, while Type II error means you tell a pregnant woman she isn’t carrying a baby.

TBD

You’ll want to do something like forward chaining where you’ll be able to model on past data then look at forward-facing data.

Fold 1 : training [1], test [2]

Fold 2 : training [1 2], test [3]

Fold 3 : training [1 2 3], test [4]

Fold 4 : training [1 2 3 4], test [5]

Fold 5 : training [1 2 3 4 5], test [6]

Reduced error pruning is perhaps the simplest version: replace each node. If it doesn’t decrease predictive accuracy, keep it pruned. While simple, this heuristic actually comes pretty close to an approach that would optimize for maximum accuracy.

Well, it has everything to do with how model accuracy is only a subset of model performance, and at that, a sometimes misleading one. For example, if you wanted to detect fraud in a massive dataset with a sample of millions, a more accurate model would most likely predict no fraud at all if only a vast minority of cases were fraud. However, this would be useless for a predictive model—a model designed to find fraud that asserted there was no fraud at all! Questions like this help you demonstrate that you understand model accuracy isn’t the be-all and end-all of model performance.

1.

Collect more data to even the imbalances in the dataset.

2.

Resample the dataset to correct for imbalances.

3.

Try a different algorithm altogether on your dataset.

What’s important here is that you have a keen sense for what damage an unbalanced dataset can cause, and how to balance that.

You could list some examples of ensemble methods (bagging, boosting, the “bucket of models” method) and demonstrate how they could increase predictive power.

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.

Machine Learning Interview Questions: Programming

These machine learning interview questions test your knowledge of programming principles you need to implement machine learning principles in practice. Machine learning interview questions tend to be technical questions that test your logic and programming skills: this section focuses more on the latter.

In Pandas, there are two very useful methods: isnull() and dropna() that will help you find columns of data with missing or corrupted data and drop those values. If you want to fill the invalid values with a placeholder value (for example, 0), you could use the fillna() method.

Machine Learning Interview Questions: Company/Industry Specific

These machine learning interview questions deal with how to implement your general machine learning knowledge to a specific company’s requirements. You’ll be asked to create case studies and extend your knowledge of the company and industry you’re applying for with your machine learning skills.

The startup metrics Slideshare linked above will help you understand exactly what performance indicators are important for startups and tech companies as they think about revenue and growth.

Machine Learning Interview Questions: General Machine Learning Interest

This series of machine learning interview questions attempts to gauge your passion and interest in machine learning. The right answers will serve as a testament to your commitment to being a lifelong learner in machine learning.

Question Set 2

1. What Are the Different Types of Machine Learning?

There are three types of machine learning:

Supervised Learning

In supervised machine learning, a model makes predictions or decisions based on past or labeled data. Labeled data refers to sets of data that are given tags or labels, and thus made more meaningful.

Unsupervised Learning

In unsupervised learning, we don't have labeled data. A model can identify patterns, anomalies, and relationships in the input data.

Reinforcement Learning

Using reinforcement learning, the model can learn based on the rewards it received for its previous action.

Consider an environment where an agent is working. The agent is given a target to achieve. Every time the agent takes some action toward the target, it is given positive feedback. And, if the action taken is going away from the goal, the agent is given negative feedback.

2. 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

3. What is ‘training Set’ and ‘test Set’ in a Machine Learning Model? How Much Data Will You Allocate for Your Training, Validation, and Test Sets?

There is a three-step process followed to create a model:

1.

Train the model

2.

Test the model

3.

Deploy the model

The training set is examples given to the model to analyze and learn

70% of the total data is typically taken as the training dataset

This is labeled data used to train the model

The test set is used to test the accuracy of the hypothesis generated by the model

Remaining 30% is taken as testing dataset

We test without labeled data and then verify results with labels

Consider a case where you have labeled data for 1,000 records. One way to train the model is to expose all 1,000 records during the training process. Then you take a small set of the same data to test the model, which would give good results in this case.

But, this is not an accurate way of testing. So, we set aside a portion of that data called the ‘test set’ before starting the training process. The remaining data is called the ‘training set’ that we use for training the model. The training set passes through the model multiple times until the accuracy is high, and errors are minimized.

Now, we pass the test data to check if the model can accurately predict the values and determine if training is effective. If you get errors, you either need to change your model or retrain it with more data.

Regarding the question of how to split the data into a training set and test set, there is no fixed rule, and the ratio can vary based on individual preferences.

4. 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

5. 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.

6. Explain the Confusion Matrix with Respect to Machine Learning Algorithms.

A confusion matrix (or error matrix) is a specific table that is used to measure the performance of an algorithm. It is mostly used in supervised learning; in unsupervised learning, it’s called the matching matrix.

The confusion matrix has two parameters:

Actual

Predicted

It also has identical sets of features in both of these dimensions.

Consider a confusion matrix (binary matrix) shown below:

Here,

For actual values:

Total Yes = 12+1 = 13

Total No = 3+9 = 12

Similarly, for predicted values:

Total Yes = 12+3 = 15

Total No = 1+9 = 10

For a model to be accurate, the values across the diagonals should be high. The total sum of all the values in the matrix equals the total observations in the test data set.

For the above matrix, total observations = 12+3+1+9 = 25

Now, accuracy = sum of the values across the diagonal / total dataset

= (12+9) / 25

= 21 / 25

= 84%

7. 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.

So, looking at the confusion matrix, we get:

False-positive = 3

True positive = 12

Similarly, in the term ‘False Negative,’ the word ‘Negative’ refers to the ‘No’ row of the predicted value in the confusion matrix. And the complete term indicates that the system has predicted it as negative, but the actual value is positive.

So, looking at the confusion matrix, we get:

False Negative = 1

True Negative = 9

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

The three stages of building a machine learning model are:

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

Check the accuracy of the model through the test data

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.

9. What is Deep Learning?

Deep learning is a subset of machine learning that involves systems that think and learn like humans using artificial neural networks. The term ‘deep’ comes from the fact that you can have several layers of neural networks.

One of the primary differences between machine learning and deep learning is that feature engineering is done manually in machine learning. In the case of deep learning, the model consisting of neural networks will automatically determine which features to use (and which not to use).

10. What Are the Differences Between Machine Learning and Deep Learning?

Enables machines to take decisions on their own, based on past data

It needs only a small amount of data for training

Works well on the low-end system, so you don't need large machines

Most features need to be identified in advance and manually coded

The problem is divided into two parts and solved individually and then combined

Enables machines to take decisions with the help of artificial neural networks

It needs a large amount of training data

Needs high-end machines because it requires a lot of computing power

The machine learns the features from the data it is provided

The problem is solved in an end-to-end manner

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

Applications of supervised machine learning include:

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.

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

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

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

12. 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.

13. 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 e-commerce website can suggest other items for you to buy, based on the prior purchases that you have made, spending habits, items in your wishlist, other customers’ purchase habits, and so on.

14. What is the Difference Between Supervised and Unsupervised Machine Learning?

15. What is the Difference Between Inductive Machine Learning and Deductive Machine Learning?

It observes instances based on defined principles to draw a conclusion

Example: Explaining to a child to keep away from the fire by showing a video where fire causes damage

It concludes experiences

Example: Allow the child to play with fire. If he or she gets burned, they will learn that it is dangerous and will refrain from making the same mistake again

16. Compare K-means and KNN Algorithms.

K-Means is a clustering algorithm

The points in each cluster are similar to each other, and each cluster is different from its neighboring clusters

KNN is a classification algorithm

It classifies an unlabeled observation based on its K (can be any number) surrounding neighbors

17. What Is ‘naive’ in the Naive Bayes Classifier?

The classifier is called ‘naive’ because it makes assumptions that may or may not turn out to be correct.

The algorithm assumes that the presence of one feature of a class is not related to the presence of any other feature (absolute independence of features), given the class variable.

For instance, a fruit may be considered to be a cherry if it is red in color and round in shape, regardless of other features. This assumption may or may not be right (as an apple also matches the description).

18. Explain How a System Can Play a Game of Chess Using Reinforcement Learning.

Reinforcement learning has an environment and an agent. The agent performs some actions to achieve a specific goal. Every time the agent performs a task that is taking it towards the goal, it is rewarded. And, every time it takes a step which goes against that goal or in reverse direction, it is penalized.

Earlier, chess programs had to determine the best moves after much research on numerous factors. Building a machine designed to play such games would require many rules to be specified.

With reinforced learning, we don’t have to deal with this problem as the learning agent learns by playing the game. It will make a move (decision), check if it’s the right move (feedback), and keep the outcomes in memory for the next step it takes (learning). There is a reward for every correct decision the system takes and punishment for the wrong one.

19. 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

20. How is Amazon Able to Recommend Other Things to Buy? How Does the Recommendation Engine Work?

Once a user buys something from Amazon, Amazon stores that purchase data for future reference and finds products that are most likely also to be bought, it is possible because of the Association algorithm, which can identify patterns in a given dataset.

21. When Will You Use Classification over Regression?

Classification is used when your target is categorical, while regression is used when your target variable is continuous. Both classification and regression belong to the category of supervised machine learning algorithms.

Examples of classification problems include:

Predicting yes or no

Estimating gender

Breed of an animal

Type of color

Examples of regression problems include:

Estimating sales and price of a product

Predicting the score of a team

Predicting the amount of rainfall

22. 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

23. What is a Random Forest?

A ‘random forest’ is a supervised machine learning algorithm that is generally used for classification problems. It operates by constructing multiple decision trees during the training phase. The random forest chooses the decision of the majority of the trees as the final decision.

24. Considering a Long List of Machine Learning Algorithms, given a Data Set, How Do You Decide Which One to Use?

There is no master algorithm for all situations. Choosing an algorithm depends on the following questions:

How much data do you have, and is it continuous or categorical?

Is the problem related to classification, association, clustering, or regression?

Predefined variables (labeled), unlabeled, or mix?

What is the goal?

Based on the above questions, the following algorithms can be used:

25. What is Bias and Variance in a Machine Learning Model?

Bias

Bias in a machine learning model occurs when the predicted values are further from the actual values. Low bias indicates a model where the prediction values are very close to the actual ones.

Underfitting: High bias can cause an algorithm to miss the relevant relations between features and target outputs.

Variance

Variance refers to the amount the target model will change when trained with different training data. For a good model, the variance should be minimized.

Overfitting: High variance can cause an algorithm to model the random noise in the training data rather than the intended outputs.

26. What is the Trade-off Between Bias and Variance?

The bias-variance decomposition essentially decomposes the learning error from any algorithm by adding the bias, variance, and a bit of irreducible error due to noise in the underlying dataset.

Necessarily, if you make the model more complex and add more variables, you’ll lose bias but gain variance. To get the optimally-reduced amount of error, you’ll have to trade off bias and variance. Neither high bias nor high variance is desired.

High bias and low variance algorithms train models that are consistent, but inaccurate on average.

High variance and low bias algorithms train models that are accurate but inconsistent.

27. 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)

28. 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.

29. 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:

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

30. Briefly Explain Logistic Regression.

Logistic regression is a classification algorithm used to predict a binary outcome for a given set of independent variables.

The output of logistic regression is either a 0 or 1 with a threshold value of generally 0.5. Any value above 0.5 is considered as 1, and any point below 0.5 is considered as 0.

31. Explain the K Nearest Neighbor Algorithm.

K nearest neighbor algorithm is a classification algorithm that works in a way that a new data point is assigned to a neighboring group to which it is most similar.

In K nearest neighbors, K can be an integer greater than 1. So, for every new data point, we want to classify, we compute to which neighboring group it is closest.

Let us classify an object using the following example. Consider there are three clusters:

Football

Basketball

Tennis ball

Let the new data point to be classified is a black ball. We use KNN to classify it. Assume K = 5 (initially).

Next, we find the K (five) nearest data points, as shown.

Observe that all five selected points do not belong to the same cluster. There are three tennis balls and one each of basketball and football.

When multiple classes are involved, we prefer the majority. Here the majority is with the tennis ball, so the new data point is assigned to this cluster.

32. 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.

33. 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.

34. 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.

Question Set 3

In all the ML Interview Questions that we would be going to discuss, this is one of the most basic question.

So, basically, there are three types of Machine Learning techniques:

In Machine Learning, there are various types of prediction problems based on supervised and unsupervised learning. These are classification, regression, clustering, and association. Here, we will discuss about classification and regression.

For example, imagine that we want to make predictions on the churning out customers for a particular product based on some data recorded. Either the customers will churn out or they will not. So, the labels for this would be ‘Yes’ and ‘No.’

For example, the prediction of weather condition depends on factors such as temperature, air pressure, solar radiation, elevation of the area, and distance from sea. The relation between these factors assists us in predicting the weather condition.

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.

The equation for Linear Regression:

1

Y = A + BX

Copied!

where:

Below is the **best fit line **that shows the data of weight (**Y** or the dependent variable) and height (**X** or the independent variable) of 21-years-old candidates scattered over the plot. This straight line shows the best linear relationship that would help in predicting the weight of candidates according to their height.

To get this **best fit line**, we will try to find the best values of **a** and **b**. By adjusting the values of *a *and *b*, we will try to reduce errors in the prediction of *Y*.

This is how linear regression helps in finding the linear relationship and predicting the output.

To identify the Machine Learning algorithm for our problem, we should follow the below steps:

If it is giving the output as a number, then we must use regression techniques and, if the output is a different cluster of inputs, then we should use clustering techniques.

The below diagram shows the bias–variance trade off:

Here, the desired result is the blue circle at the center. If we get off from the blue section, then the prediction goes wrong.

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.

Confusion matrix is used to explain a model’s performance and gives the summary of predictions on the classification problems. It assists in identifying the uncertainty between classes.

A confusion matrix gives the count of correct and incorrect values and also the error types.**Accuracy of the model: **

Accuracy of the model

For example, consider this confusion matrix. It consists of values as True Positive, True Negative, False Positive, and False Negative for a classification model. Now, the accuracy of the model can be calculated as follows:

What is a Confusion Matrix

Thus, in our example:

1

Accuracy = (200 + 50) / (200 + 50 + 10 + 60) = 0.78

Copied!

This means that the model’s accuracy is 0.78, corresponding to its True Positive, True Negative, False Positive, and False Negative values.

For example, a cricket match is going on and, when a batsman is not out, the umpire declares that he is out. This is a false positive condition. Here, the test does not accept the true condition that the batsman is not out.

For example, the CT scan of a person shows that he is not having a disease but, in reality, he is having it. Here, the test accepts the false condition that the person is not having the disease.

Both classification and regression are associated with prediction. Classification involves the identification of values or entities that lie in a specific group. The regression method, on the other hand, entails predicting a response value from a consecutive set of outcomes.

The classification method is chosen over regression when the output of the model needs to yield the belongingness of data points in a dataset to a particular category.

For example, we have some names of bikes and cars. We would not be interested in finding how these names are correlated to bikes and cars. Rather, we would check whether each name belongs to the bike category or to the car category.

Logistic regression is the proper regression analysis used when the dependent variable is categorical or binary. Like all regression analyses, logistic regression is a technique for predictive analysis. Logistic regression is used to explain data and the relationship between one dependent binary variable and one or more independent variables. Also, it is employed to predict the probability of a categorical dependent variable.

We can use logistic regression in the following scenarios:

To predict whether a citizen is a Senior Citizen (1) or not (0)

To check whether a person is having a disease (Yes) or not (No)

There are three types of logistic regression:

To deal with the missing values, we will do the following:

We will specify a different class for the missing values.

Now, we will check the distribution of values, and we would hold those missing values that are defining a pattern.

Then, we will charge these into a yet another class, while eliminating others.

In Python Pandas, there are two methods that are very useful. We can use these two methods to locate the lost or corrupted data and discard those values:

Also, we can use **fillna() **to fill the void values with a placeholder value.

Firstly, this is one of the most important Machine Learning Interview Questions.

In the real world, we deal with multi-dimensional data. Thus, data visualization and computation become more challenging with the increase in dimensions. In such a scenario, we might have to reduce the dimensions to analyze and visualize the data easily. We do this by:

Removing irrelevant dimensions

Keeping only the most relevant dimensions

This is where we use Principal Component Analysis (PCA).

Finding a fresh collection of uncorrelated dimensions (orthogonal) and ranking them on the basis of variance are the goals of Principal Component Analysis.

Compute the covariance matrix for data objects

Compute the Eigen vectors and the Eigen values in a descending order

To get the new dimensions, select the initial *N* Eigen vectors

Finally, change the initial n-dimensional data objects into N-dimensions

Explain Principal Component Analysis (PCA)

Output from PCA

After the rotation of the data points, we can infer that the green direction (x-axis) gives us the line that best fits the data points.

Here, we are representing 2-dimensional data. But in real-life, the data would be multi-dimensional and complex. So, after recognizing the importance of each direction, we can reduce the area of dimensional analysis by cutting off the less-significant ‘directions.’

Now, we will look into another important Machine Learning Interview Question on PCA.

Rotation is a significant step in PCA as it maximizes the separation within the variance obtained by components. Due to this, the interpretation of components becomes easier.

The motive behind doing PCA is to choose fewer components that can explain the greatest variance in a dataset. When rotation is performed, the original coordinates of the points get changed. However, there is no change in the relative position of the components.

If the components are not rotated, then we need more extended components to describe the variance.

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.

In **label encoding**, the sub-classes of a certain variable get the value as **0** and **1**. So, we use label encoding only for binary variables.

This is the reason that one hot encoding increases the dimensionality of data and label encoding does not.

Overfitting happens when a machine has an inadequate dataset and it tries to learn from it. So, overfitting is inversely proportional to the amount of data.

For small databases, we can bypass overfitting by the cross-validation method. In this approach, we will divide the dataset into two sections. These two sections will comprise testing and training sets. To train the model, we will use the training dataset and, for testing the model for new inputs, we will use the testing dataset.

This is how we can avoid overfitting.

We split the data into three different categories while creating a model:

1.

2.

When we are evaluating the model’s response using the validation set, we are indirectly training the model with the validation set. This may lead to the overfitting of the model to specific data. So, this model won’t be strong enough to give the desired response to the real-world data.

1.

As we know, the evaluation of the model on the basis of the validation set would not be enough. Thus, we use a test set for computing the efficiency of the model.

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 a Decision Tree

We can create an algorithm for a decision tree on the basis of the hierarchy of actions that we have set.

In the above decision tree diagram, we have made a sequence of actions for driving a vehicle with/without a license.

K-nearest neighbors

K-means clustering

In the real world, we build Machine Learning models on top of features and parameters. These features can be multi-dimensional and large in number. Sometimes, the features may be irrelevant and it becomes a difficult task to visualize them.

Here, we use dimensionality reduction to cut down the irrelevant and redundant features with the help of principal variables. These principal variables are the subgroup of the parent variables that conserve the feature of the parent variables.

The main difference between a random forest and GBM is the use of techniques. Random forest advances predictions using a technique called ‘bagging.’ On the other hand, GBM advances predictions with the help of a technique called ‘boosting.’

For handling issues of high variance, we should use the bagging algorithm.

Bagging algorithm would split data into sub-groups with replicated sampling of random data.

Once the algorithm splits the data, we use random data to create rules using a particular training algorithm.

After that, we use polling for combining the predictions of the model.

ROC stands for ‘Receiver Operating Characteristic.’ We use ROC curves to represent the trade-off between True and False positive rates, graphically.

In ROC, AUC (Area Under the Curve) gives us an idea about the accuracy of the model.

The above graph shows an ROC curve. Greater the Area Under the Curve better the performance of the model.

Next, we would be looking at Machine Learning Interview Questions on Rescaling, Binarizing, and Standardizing.

In real-world scenarios, the attributes present in data will be in a varying pattern. So, rescaling of the characteristics to a common scale gives benefit to algorithms to process the data efficiently.

We can rescale the data using Scikit-learn. The code for rescaling the data using MinMaxScaler is as follows:

1

#Rescaling data

2

import pandas

3

import scipy

4

import numpy

5

6

from sklearn.preprocessing import MinMaxScaler

7

8

names = ['Abhi', 'Piyush', 'Pranay', 'Sourav', 'Sid', 'Mike', 'pedi', 'Jack', 'Tim']

9

Dataframe = pandas.read_csv(url, names=names)

10

Array = dataframe.values

11

12

# Splitting the array into input and output

13

X = array[:,0:8]

14

Y = array[:,8]

15

16

Scaler = MinMaxScaler(feature_range=(0, 1))

17

rescaledX = scaler.fit_transform(X)

18

19

# Summarizing the modified data

20

numpy.set_printoptions(precision=3)

21

print(rescaledX[0:5,:])

Copied!

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

We can binarize data using Scikit-learn. The code for binarizing the data using Binarizer is as follows:

1

from sklearn.preprocessing import Binarizer

2

import pandas

3

import numpy

4

names = ['Abhi', 'Piyush', 'Pranay', 'Sourav', 'Sid', 'Mike', 'pedi', 'Jack', 'Tim']

5

dataframe = pandas.read_csv(url, names=names)

6

array = dataframe.values

7

# Splitting the array into input and output

8

X = array[:,0:8]

9

Y = array[:,8]

10

binarizer = Binarizer(threshold=0.0).fit(X)

11

binaryX = binarizer.transform(X)

12

# Summarizing the modified data

13

numpy.set_printoptions(precision=3)

14

print(binaryX[0:5,:])

Copied!

Standardization is the method that is used for rescaling data attributes. The attributes would likely have a value of mean as **0** and the value of standard deviation as **1**. The main objective of standardization is to prompt the mean and standard deviation for the attributes.

We can standardize the data using Scikit-learn. The code for standardizing the data using StandardScaler is as follows:

1

# Python code to Standardize data (0 mean, 1 stdev)

2

from sklearn.preprocessing import StandardScaler

3

import pandas

4

import numpy

5

names = ['Abhi', 'Piyush', 'Pranay', 'Sourav', 'Sid', 'Mike', 'pedi', 'Jack', 'Tim']

6

dataframe = pandas.read_csv(url, names=names)

7

array = dataframe.values

8

# Separate the array into input and output components

9

X = array[:,0:8]

10

Y = array[:,8]

11

scaler = StandardScaler().fit(X)

12

rescaledX = scaler.transform(X)

13

# Summarize the transformed data

14

numpy.set_printoptions(precision=3)

15

print(rescaledX[0:5,:])

Copied!

Gini index and Node Entropy assist the binary classification tree to take decisions. Basically, the tree algorithm determines the feasible feature that is used to distribute data into the most genuine child nodes.

According to Gini index, if we arbitrarily pick a pair of objects from a group, then they should be of identical class and the possibility for this event should be **1**.

To compute the Gini index, we should do the following:

1.

Compute Gini for sub-nodes with the formula: The sum of the square of probability for success and failure (p^2 + q^2)

2.

Compute Gini for split by weighted Gini rate of every node of the split

Now, Entropy is the degree of indecency that is given by the following:

where **a** and **b** are the probabilities of success and failure of the node

When** Entropy = 0**, the node is homogenous

When** Entropy is high**, both groups are present at 50–50 percent in the node.

Finally, to determine the suitability of the node as a root node, the entropy should be very low.

SVM is a Machine Learning algorithm that is majorly used for classification. It is used on top of the high dimensionality of the characteristic vector.

Below is the code for the SVM classifier:

1

# Introducing required libraries

2

from sklearn import datasets

3

from sklearn.metrics import confusion_matrix

4

from sklearn.model_selection import train_test_split

5

# Stacking the Iris dataset

6

iris = datasets.load_iris()

7

# A -> features and B -> label

8

A = iris.data

9

B = iris.target

10

# Breaking A and B into train and test data

11

A_train, A_test, B_train, B_test = train_test_split(A, B, random_state = 0)

12

# Training a linear SVM classifier

13

from sklearn.svm import SVC

14

svm_model_linear = SVC(kernel = 'linear', C = 1).fit(A_train, B_train)

15

svm_predictions = svm_model_linear.predict(A_test)

16

# Model accuracy for A_test

17

accuracy = svm_model_linear.score(A_test, B_test)

18

# Creating a confusion matrix

19

cm = confusion_matrix(B_test, svm_predictions)

Copied!

We will use the Iris dataset for implementing the KNN classification algorithm.

1

# KNN classification algorithm

2

from sklearn.datasets import load_iris

3

from sklearn.neighbors import KNeighborsClassifier

4

import numpy as np

5

from sklearn.model_selection import train_test_split

6

iris_dataset=load_iris()

7

A_train, A_test, B_train, B_test = train_test_split(iris_dataset["data"], iris_dataset["target"], random_state=0)

8

kn = KNeighborsClassifier(n_neighbors=1)

9

kn.fit(A_train, B_train)

10

A_new = np.array([[8, 2.5, 1, 1.2]])

11

prediction = kn.predict(A_new)

12

print("Predicted target value: {}\n".format(prediction))

13

print("Predicted feature name: {}\n".format

14

(iris_dataset["target_names"][prediction]))

15

print("Test score: {:.2f}".format(kn.score(A_test, B_test)))

16

Output:

17

Predicted Target Name: [0]

18

Predicted Feature Name: [‘ Setosa’]

19

Test Score: 0.92

20

Copied!

Question Set 4

Artificial Intelligence (AI) is the domain of producing intelligent machines. ML refers to systems that can assimilate from experience (training data) and Deep Learning (DL) states to systems that learn from experience on large data sets. ML can be considered as a subset of AI. Deep Learning (DL) is ML but useful to large data sets. The figure below roughly encapsulates the relation between AI, ML, and DL:

In summary, DL is a subset of ML & both were the subsets of AI.

Additional Information: ASR (Automatic Speech Recognition) & NLP (Natural Language Processing) fall under AI and overlay with ML & DL as ML is often utilized for NLP and ASR tasks.

ML algorithms can be primarily classified depending on the presence/absence of target variables.

Machine Learning involves algorithms that learn from patterns of data and then apply it to decision making. Deep Learning, on the other hand, is able to learn through processing data on its own and is quite similar to the human brain where it identifies something, analyse it, and makes a decision.
The key differences are as follow:

The manner in which data is presented to the system.

Machine learning algorithms always require structured data and deep learning networks rely on layers of artificial neural networks.

Supervised learning technique needs labeled data to train the model. For example, to solve a classification problem (a supervised learning task), you need to have label data to train the model and to classify the data into your labeled groups. Unsupervised learning does not need any labelled dataset. This is the main key difference between supervised learning and unsupervised learning.

There are various means to select important variables from a data set that include the following:

Identify and discard correlated variables before finalizing on important variables

The variables could be selected based on ‘p’ values from Linear Regression

Forward, Backward, and Stepwise selection

Lasso Regression

Random Forest and plot variable chart

Top features can be selected based on information gain for the available set of features.

Machine Learning algorithm to be used purely depends on the type of data in a given dataset. If data is linear then, we use linear regression. If data shows non-linearity then, the bagging algorithm would do better. If the data is to be analyzed/interpreted for some business purposes then we can use decision trees or SVM. If the dataset consists of images, videos, audios then, neural networks would be helpful to get the solution accurately.

So, there is no certain metric to decide which algorithm to be used for a given situation or a data set. We need to explore the data using EDA (Exploratory Data Analysis) and understand the purpose of using the dataset to come up with the best fit algorithm. So, it is important to study all the algorithms in detail.

Covariance measures how two variables are related to each other and how one would vary with respect to changes in the other variable. If the value is positive it means there is a direct relationship between the variables and one would increase or decrease with an increase or decrease in the base variable respectively, given that all other conditions remain constant.

Correlation quantifies the relationship between two random variables and has only three specific values, i.e., 1, 0, and -1.

1 denotes a positive relationship, -1 denotes a negative relationship, and 0 denotes that the two variables are independent of each other.

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.

We have to build ML algorithms in System Verilog which is a Hardware development Language and then program it onto an FPGA to apply Machine Learning to hardware.

One-hot encoding is the representation of categorical variables as binary vectors. Label Encoding is converting labels/words into numeric form. Using one-hot encoding increases the dimensionality of the data set. Label encoding doesn’t affect the dimensionality of the data set. One-hot encoding creates a new variable for each level in the variable whereas, in Label encoding, the levels of a variable get encoded as 1 and 0.

Deep Learning is a part of machine learning that works with neural networks. It involves a hierarchical structure of networks that set up a process to help machines learn the human logics behind any action. We have compiled a list of the frequently asked deep leaning interview questions to help you prepare.

Overfitting is a type of modelling error which results in the failure to predict future observations effectively or fit additional data in the existing model. It occurs when a function is too closely fit to a limited set of data points and usually ends with more parameters

The Boltzmann machine is a simplified version of the multilayer perceptron. This is a two layer model with a visible input layer and a hidden layer which makes stochastic decisions

At times when the model begins to underfit or overfit, regularization becomes necessary. It is a regression that diverts or regularizes the coefficient estimates towards zero. It reduces flexibility and discourages learning in a model to avoid the risk of overfitting. The model complexity is reduced and it becomes better at predicting.

Both are errors in Machine Learning Algorithms. When the algorithm has limited flexibility to deduce the correct observation from the dataset, it results in bias. On the other hand, variance occurs when the model is extremely sensitive to small fluctuations.

If one adds more features while building a model, it will add more complexity and we will lose bias but gain some variance. In order to maintain the optimal amount of error, we perform a tradeoff between bias and variance based on the needs of a business.

Bias stands for the error because of the erroneous or overly simplistic assumptions in the learning algorithm . This assumption can lead to the model underfitting the data, making it hard for it to have high predictive accuracy and for you to generalize your knowledge from the training set to the test set.

Variance is also an error because of too much complexity in the learning algorithm. This can be the reason for the algorithm being highly sensitive to high degrees of variation in training data, which can lead your model to overfit the data. Carrying too much noise from the training data for your model to be very useful for your test data.

The bias-variance decomposition essentially decomposes the learning error from any algorithm by adding the bias, the variance and a bit of irreducible error due to noise in the underlying dataset. Essentially, if you make the model more complex and add more variables, you’ll lose bias but gain some variance — in order to get the optimally reduce