// ✦ Diffusion, Flow Matching & Generative Models
Generative Adversarial Network (GAN)
A generator and a discriminator improve by competing.
生成对抗网络 GAN 2014 Intermediate extended
IN PLAIN WORDS
The generator turns noise into samples to fool the discriminator, which learns to tell real from fake; equilibrium matches the data distribution. Dominant before diffusion; still used for super-resolution and distillation.
Used in: StyleGAN, super-resolution
01Original paper
Generative Adversarial Networks
Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, et al. · 2014
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Then you can learn
- Nothing in the atlas builds on it yet
Related:Denoising Diffusion Probabilistic Models (DDPM)Variational Autoencoder (VAE)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
gan)