Generative Adversarial Network (GAN) Deep Learning
noun phrase
Definition: A generative modeling framework in which a generator and a discriminator are trained simultaneously in an adversarial process, with the generator aiming to produce samples indistinguishable from real data [Goodfellow et al. 2014].
Example in context: “In Florensa et al. (2018), a Generative Adversarial Network (gan) is trained on past representations of states (φ(s)) to model a distribution of goals and thus its support.” [Colas 2022]
Synonym: GAN
Related terms: generator, discriminator, adversarial training