A class of machine learning frameworks where two neural networks contest with each other in a game to generate new, synthetic instances of data.
Generative Adversarial Networks (GANs) pair a generator, which creates synthetic data, with a discriminator, which tries to tell it apart from real data. This adversarial loop has been widely used to generate realistic synthetic data, for example to train autonomous systems or to augment datasets in privacy-constrained environments.
See also Synthetic Data, Large Language Model, Fine-Tuning and Model Inference.