CS CS Artificial Intelligence & Machine Learning

Question 1

Which type of machine learning algorithm learns from labeled training data to predict outcomes on new data?

Accepted Answer

Supervised Learning

Answer

Reinforcement Learning

Answer

Unsupervised Learning

Answer

Self-supervised Learning

Question 2

What is the vanishing gradient problem in deep neural networks?

Accepted Answer

Gradients shrink exponentially as they propagate backward, halting learning in early layers

Answer

Weights grow too large during backpropagation

Answer

The network overfits to training data

Answer

Activation functions return zero for all inputs

Question 3

In a decision tree, what does 'pruning' accomplish?

Accepted Answer

Removes branches to reduce overfitting and improve generalization

Answer

Adds more leaf nodes to increase accuracy

Answer

Reorders tree branches alphabetically

Answer

Duplicates subtrees to improve recall

Question 4

Which distance metric is most commonly used in k-Nearest Neighbors (kNN) for continuous features?

Accepted Answer

Euclidean Distance

Answer

Hamming Distance

Answer

Jaccard Distance

Answer

Cosine Similarity

Question 5

What is the purpose of a confusion matrix in evaluating a classification model?

Accepted Answer

It shows the breakdown of true/false positives and negatives to assess classification performance

Answer

It visualizes the loss curve during training

Answer

It measures the correlation between input features

Answer

It displays the weights of each neuron in the network

Question 6

In reinforcement learning, what is the role of the 'reward' signal?

Accepted Answer

It provides feedback to the agent indicating how good or bad a taken action was

Answer

It initializes the agent's policy to a known good state

Answer

It sets the learning rate for the neural network

Answer

It defines the action space available to the agent