Generative Adversarial Network (GAN)
A framework where two neural networks (generator and discriminator) compete to create realistic synthetic data.
Detailed Explanation
Generative Adversarial Networks consist of two neural networks—a generator and a discriminator—that are trained simultaneously through adversarial competition. The generator creates synthetic data samples, while the discriminator evaluates them against real data, trying to distinguish between real and fake. The generator aims to fool the discriminator by producing increasingly realistic samples, while the discriminator improves at detecting fakes. This adversarial process drives both networks to improve until the generator produces samples that are indistinguishable from real data. GANs have been particularly successful in generating realistic images, though they can be challenging to train due to instability issues.
Examples
- StyleGAN for face generation
- CycleGAN for image-to-image translation
- Text-to-image GANs