MS-DS Master of Data science MS-DS Master of Data science Supervised Learning Algorithms Questions and Answers 2

Question 1

Which supervised learning algorithm uses the concept of maximum margin to separate classes?

Accepted Answer

Support Vector Machine

Answer

Naive Bayes

Answer

K-Nearest Neighbors

Answer

Logistic Regression

Question 2

In gradient boosting, what does each subsequent tree attempt to predict?

Accepted Answer

The residual errors of the previous model

Answer

The original target variable

Answer

The feature importances

Answer

The learning rate

Question 3

What is the primary assumption of the Naive Bayes classifier?

Accepted Answer

Features are conditionally independent given the class label

Answer

The decision boundary is linear

Answer

All features have equal variance

Answer

The data is normally distributed

Question 4

Which regularization technique in linear regression can shrink coefficients exactly to zero, enabling feature selection?

Accepted Answer

L1 (Lasso)

Answer

L2 (Ridge)

Answer

Elastic Net

Answer

Dropout

Question 5

What problem does the kernel trick solve in Support Vector Machines?

Accepted Answer

It allows SVMs to find non-linear decision boundaries without explicitly mapping to higher dimensions

Answer

It reduces overfitting by adding a penalty term

Answer

It speeds up training on large datasets

Answer

It handles missing values in the feature space

Question 6

In a Random Forest, what technique is used to ensure diversity among individual decision trees?

Accepted Answer

Bagging with random feature subsets at each split

Answer

Boosting with adaptive weights

Answer

Stacking with a meta-learner

Answer

Pruning with cross-validation