Which of the following is NOT a type of machine learning?

What does PAC stand for in machine learning?

Which metric is used for splitting in ID3 algorithm?

What is the key assumption of Naive Bayes?

Which technique helps reduce overfitting in decision trees?

Which of these is a distance metric used in clustering?

What is the main advantage of Random Forest over single decision trees?

Which learning algorithm uses a reward-punishment mechanism?

Which technique combines multiple weak learners to create a strong learner?

What is the purpose of the kernel trick in SVM?

Which evaluation metric is most appropriate for imbalanced datasets?

What is the main limitation of KNN algorithm?

Which algorithm is most suitable for anomaly detection?

Which technique helps handle missing values in datasets?

What is the key difference between bagging and boosting?

Which neural network architecture is best for image processing?

What does the ELBO stand for in variational inference?

Which activation function helps mitigate vanishing gradients?

Which regularization technique adds absolute values of weights to loss?

What is the key advantage of batch normalization?

Which algorithm would you choose for text classification?

What is the purpose of the attention mechanism in transformers?

Which evaluation metric is most important for medical diagnosis?

What does the Bellman equation optimize in RL?

Which technique prevents overfitting in neural networks?

Explain the bias-variance tradeoff with examples of high-bias and high-variance models. How does regularization address this?

Compare ID3, C4.5 and CART algorithms. Explain their splitting criteria, handling of continuous features, and pruning methods.

Derive the E-step and M-step equations for Gaussian Mixture Models. How does the EM algorithm guarantee convergence?

Explain Q-learning with the Bellman equation. How does it differ from policy gradient methods in terms of exploration strategies?