Machine Learning Deep Learning 4

Question 1

In a generative adversarial network (GAN), what is the role of the discriminator?

Accepted Answer

To distinguish between real and generated samples

Answer

The discriminator is a classifier trained to tell apart real data from fake data produced by the generator, providing adversarial feedback.

Question 2

What does the term 'epoch' mean in neural network training?

Accepted Answer

One complete pass through the entire training dataset

Answer

An epoch is completed when the model has seen every sample in the training set exactly once, typically composed of multiple mini-batch updates.

Question 3

What is the primary difference between L1 and L2 regularization in deep learning?

Accepted Answer

L1 penalizes the sum of absolute weights, promoting sparsity; L2 penalizes squared weights

Answer

L1 regularization adds |w| to the loss, driving some weights to exactly zero (sparsity), while L2 adds w² and shrinks weights uniformly.

Question 4

Which optimizer adapts the learning rate for each parameter based on past gradients and is commonly used in training transformers?

Accepted Answer

Adam

Answer

Adam combines momentum and RMSProp, maintaining adaptive per-parameter learning rates using first and second moment estimates of gradients.

Question 5

What is a hyperparameter in the context of training a deep neural network?

Accepted Answer

A configuration value set before training that controls the learning process

Answer

Hyperparameters like learning rate, batch size, and number of layers are chosen before training and are not updated by the optimizer.

Machine Learning Practice Test