Generative Adversarial Network
Visualize the generator mapping latent noise to a target distribution while the discriminator learns to separate real from fake.
Free theory articleVisualize the generator mapping latent noise to a target distribution while the discriminator learns to separate real from fake.
Concept & interpretation
A Generative Adversarial Network (GAN) is an architecture in machine learning consisting of two neural networks—the Generator and the Discriminator—that compete against each other in a zero-sum game. The Generator attempts to produce fake data that is indistinguishable from real data, while the Discriminator attempts to correctly distinguish between the real and generated data. Over time, this adversarial training forces the Generator to learn the underlying distribution of the real data.