GANs, or Generative Adversarial Networks, are a class of machine learning frameworks introduced by Ian Goodfellow and his colleagues in 2014. The fundamental idea behind GANs is to set up a game between two models: a generator and a discriminator. 1. **Generator**: This model generates new data instances. It takes random noise as input and tries to produce data that mimics the actual distribution of the training data.
New to topics? Read the docs here!