generative adversarial Network (GAN)

A generative adversarial network (GAN) is a type of machine learning model that consists of two neural networks — the generator and the discriminator — which are trained in an adversarial manner. The generator creates synthetic data, while the discriminator evaluates that generated data, trying to distinguish between genuine and generated samples.

The two networks essentially play a game: the generator aims to produce data that is indistinguishable from real data, and the discriminator aims to get better at telling the difference. This process continues until the generator produces results that the discriminator can no longer reliably classify as fake, resulting in the generation of new, realistic data.

Citations:

https://www.techtarget.com/searchenterpriseai/definition/generative-adversarial-network-GAN

https://en.wikipedia.org/wiki/Generative_adversarial_network

https://aws.amazon.com/what-is/gan/

https://www.techopedia.com/definition/32515/generative-adversarial-network-gan

https://machinelearningmastery.com/what-are-generative-adversarial-networks-gans/

https://deepai.org/machine-learning-glossary-and-terms/generative-adversarial-network

https://www.geeksforgeeks.org/generative-adversarial-network-gan/