Chapter 2

Generative Adversarial Networks

GANs pit two neural networks against each other in a zero-sum game: a generator that creates fake samples and a discriminator that tries to tell real from fake. When trained together, the generator learns to produce outputs that are indistinguishable from real data. This chapter covers the setup, the min-max training objective from Goodfellow et al. (2014), the common training pathologies (vanishing gradients, mode collapse, instability), and the conditional GAN extensions that unlock text-to-image, image-to-image, and super-resolution applications.

• 1. The GAN Framework→
• 2. Adversarial Training and the Min-Max Objective→
• 3. Conditional GANs and Applications→