a$.$ What is the difference between train, validation, and test sets?

b$.$ What's the risk with tuning hyperparameters using a test dataset?

c$.$ What is the role of pooling layers in a CNN$?$

d$.$ If somebody tells you, "Overfitting is bad, so you want to make sure your model

is simple enough that the test error is no higher than the training error." Is this

statement right or wrong?

e$.$ What is the role of dropout in neural network training?

f$.$ Explain the concept of batch normalization and its two potential bencfits.

g$.$ How does transfer learning contribute to the training of deep networks?