GAN

Definition	:	Generative Adversarial Network
Category	:	Computing » Programming & Development
Country/Region	:	Worldwide
Popularity	:
Type	:	Acronym

What does GAN mean?

Generative Adversarial Network (GAN) is a Machine Learning (ML) model used in unsupervised learning. GAN works by two neural networks consist of a generator and a discriminator competing against each other in a zero-sum game framework to become more accurate in their predictions.
In GAN, the generator will constantly try to outsmart the discriminator by generating better and better fakes, while the discriminator tries to become a better detective and correctly classify the real and fake data from the output of the generator.