GAN

A deep learning framework in which two networks — a generator and a discriminator — compete to produce increasingly realistic synthetic data. A Generative Adversarial Network (GAN) is a generative model architecture introduced by Ian Goodfellow in 2014 that trains two neural networks in opposition: a generator that creates synthetic samples, and a discriminator that tries to distinguish real from generated samples.

Through adversarial training, the generator learns to produce increasingly realistic outputs as the discriminator becomes more discerning, until the generator's outputs are indistinguishable from real data.

Generative Adversarial Network is a foundational concept in Model Architecture. A deep learning framework in which two networks — a generator and a discriminator — compete to produce increasingly realistic synthetic data.