Model Components
Generative Adversarial Network (GAN)
Introduced by Ian Goodfellow in 2014, GANs pit a generator (which creates fake data) against a discriminator (which tries to distinguish real from fake). The generator improves by fooling the discriminator; the discriminator improves by correctly identifying fakes. This adversarial training produces increasingly realistic outputs.
GANs enabled photorealistic image synthesis, deepfakes, and style transfer. For text, GANs are less common due to the discrete nature of tokens making gradient flow difficult. Diffusion models have largely superseded GANs for image generation.
Authority Links
Related Terms
Model Components
Generator
GAN component that creates synthetic data instances designed to be indistinguishable from real data.
Model Components
Discriminator (in GAN)
GAN component that learns to distinguish real data from fake data generated by the generator.
Model Components
Generative Model
AI model that learns to generate new data instances resembling the training distribution.
Techniques & Methods
Adversarial Training
Training AI models on challenging, adversarially crafted inputs to improve robustness and reliability.