GAN (Generative Adversarial Network)
Two neural networks trained against each other: a generator produces artificial data and a discriminator tries to tell it apart from real data. Introduced by Ian Goodfellow and colleagues in 2014.
A generative adversarial network (GAN) pairs two neural networks: a generator that maps random noise into synthetic samples, and a discriminator that tries to tell real training data from fakes. The generator is trained to fool the discriminator, framing learning as a minimax two-player game.
When both nets are multilayer perceptrons, the system can be trained with backpropagation, without Markov chains or unrolled inference networks. GANs became a major strand of generative AI and unsupervised learning. See the article and timeline entry.