Too Long; Didn't Read
Generative adversarial networks (GANs) learn the structure of complex real-world data examples and generate similar examples that are bound by the same structure. Generative-adversarial networks consist of two parts: **generative** and **discriminative** The generative neural network creates samples, and the discriminative tries to distinguish correct samples from incorrect ones. GANs include both a. generative and a discrim. model, generative models can exist separately and be used for different tasks. However, only generative. models are able to create novel data samples.