True or false: the discriminator network and generator network influence
each other solely through the data produced by the generator and the labels
produced by the discriminator. When it comes to backpropagation, they
are separate networks.
True
Incorrect: during generator training, gradients propagate through the
discriminator network to the generator network (although the discriminator
does not update its weights during generator training).
False
Correct: during generator training, gradients propagate through the
discriminator network to the generator network (although the discriminator
does not update its weights during generator training). So the weights in
the discriminator network influence the updates to the generator network.
True or false: a typical GAN trains the generator and the discriminator
simultaneously.
True
Incorrect. A typical GAN alternates between training the discriminator
and training the generator. There is some [research
](https://arxiv.org/abs/1706.04156) on training the
generator and discriminator simultaneously.
False
Correct. A typical GAN alternates between training the discriminator
and training the generator.
True or false: a GAN always uses the same loss function for both
discriminator and generator training.
True
Incorrect. While it's possible for a GAN to use the same loss for
both generator and discriminator training (or the same loss differing only
in sign), it's not required. In fact it's more common to use different
losses for the discriminator and the generator.
False
Correct. While it's possible for a GAN to use the same loss for
both generator and discriminator training (or the same loss differing only
in sign), it's not required. In fact it's more common to use different
losses for the discriminator and the generator.