QUESTION $4$

A generative adversarial network is a neural network architecture composed of two parts, the generator and the discriminator, which have opposing objectives

True

False

QUESTION $5$

Generator weights are updated duing discriminator training

True

False

QUESTION $6$

At each training iteration, the discriminator is trained like a normal binary classifier, then the generator is trained to maximize the discriminator's error.

True

False

QUESTION $7$

Training GANs is simple, because of the lack of dynamics between the generator and the discriminator.

True

$$ False

$q,$

QUESTION $8$

G$.$ANs are very sensitive to the choice of hyperparameters.

True

False

$q,$

$q,$

QUESTION $9$

When using Progressive Growing of GANs in order to avoid mode collapse you can use:

Equalized Leaming Rate

Minibatch Standard Deviation Layer

Pixelwise Normalization Layer

$q,$

QUESTION $10$

A Synthesis Network when using SbyleGANs, is tasked with generating the images.

True

False