Information Technology

Gartner Glossary

Generative Adversarial Networks (GANs)

Generative adversarial networks (GANs) are used after training to generate totally novel media content, synthetic data, and models of physical objects that preserve the likeness of the original data. GANs are composed of two neural networks: one — called the generator — specializes in generating objects of a specific type (e.g., images of human faces or dogs, or models of molecules); the other — the discriminator — learns to evaluate them as real or fake.