Description

Generative Adversarial Networks (GANs) are a class of machine learning frameworks introduced by Ian Goodfellow and his colleagues in 2014. In a GAN, two neural networks contest with each other in a game. The generator network creates candidates (typically images), while the discriminator network evaluates them. The contest drives both networks to improve their performance until the generated images are indistinguishable from genuine images.

Examples

• 🎭 DeepFake videos
• 🎨 Art generation
• 🔄 Data augmentation

Applications