Why does Batch Normalization include a scale and shift transformation after normalization?

Why are Xavier and He initializations important when training deep neural networks?

One epoch in training refers to what?

Which of the following is NOT an example of a wrapper method?

Which component of the neural network adjusts model parameters to minimize the loss function?

Which option correctly states what “bagging” stands for and how its predictions are aggregated in regression vs. classification?

Which statement best defines feature engineering in the context of machine learning?

Which activation function is least likely to suffer from vanishing or exploding gradients in deep networks?

Which statement best describes an embedded feature-selection method?

When using ______ logic that only one expression must evaluate to True for the entire expression to be True.