the generator and discriminator losses derive from a single measure of distance between probability distributions. In both of these schemes, however, the generator can only affect one term in the distance measure: the term that reflects the distribution of the fake data. So during generator training we drop the other term, which reflects the distribution of the real data.

So we train the generator with the following procedure: Sample random noise. Produce generator output from sampled random noise. Get discriminator "Real" or "Fake" classification for generator output. Calculate loss from discriminator classification. Backpropagate through both the discriminator and generator to obtain gradients. Use gradients to change only the generator weights.

The portion of the GAN that trains the generator includes: random input generator network, which transforms the random input into a data instance discriminator network, which classifies the generated data discriminator output generator loss, which penalizes the generator for failing to fool the discriminator

generator part of a GAN learns to create fake data by incorporating feedback from the discriminator

During discriminator training the generator does not train. Its weights remain constant while it produces examples for the discriminator to train on.

Both the generator and the discriminator are neural networks. The generator output is connected directly to the discriminator input. Through backpropagation, the discriminator's classification provides a signal that the generator uses to update its weights.

generated instances become negative training examples for the discriminator

Discriminative models try to draw boundaries in the data space, while generative models try to model how data is placed throughout the space.