Generator vs Discriminator: The Game
Two networks competing to improve.
Two Networks, One Game
A GAN is two neural networks playing a game: one invents fake data, the other tries to catch it. Their rivalry is what makes both improve. 🎭
Meet the Generator
The generator starts with random noise and shapes it into something that looks like real data, such as a fake face. It never sees the real images directly.
All lessons in this course
- Generator vs Discriminator: The Game
- The Adversarial Loss
- Build a DCGAN
- Mode Collapse & Stabilizing Tricks