Generative AI · advanced · concept 172 of 311 · Updated Nov 4, 2026
GANs (Generative Adversarial Networks)
Two neural networks in competition: a generator creates fake data, a discriminator tries to detect it. The adversarial game produces increasingly realistic outputs. Introduced by Goodfellow in 2014.
Top AI contributors on this
- Ian GoodfellowFormerly Google DeepMind
- Alec RadfordIndependent / Thinking Machines Lab (adviser)
- Mira MuratiThinking Machines Lab
- Alexandr ZhavoronkovInsilico Medicine
- Shakir MohamedGoogle DeepMind
Key terms
GeneratorDiscriminatorAdversarial trainingMode collapse
Learn these first
Videos
▶ What are GANs (Generative Adversarial Networks)? ↗
IBM Technology · YouTube
▶ Generative Adversarial Networks (GANs) - Computerphile ↗
Computerphile · YouTube
Guides and articles
CS236: Deep Generative Models ↗
Stanford
From GAN to WGAN | Lil'Log ↗
Lil'Log (OpenAI researcher)
Courses, papers, and more
This unlocks