What is Generative adversarial network (GAN)?

Generative adversarial network (GAN)

Generative adversarial network (GAN): A pair of networks trained together, a generator making samples and a discriminator judging them, competing until outputs look realistic.

Related terms

Adversarial example
Adversarial suffix
Convolutional neural network (CNN)
Deep Q-network (DQN)
Discriminator (GAN)
Expert network
Feedforward network (FFN)
Generative engine optimisation (GEO)

Browse the full glossary →