GLOSSARY TERM

What is Generative Adversarial Network?

A class of frameworks consisting of a generator and a discriminator network.
GANs pit two neural networks against each other. The generator attempts to create realistic synthetic data, while the discriminator evaluates its authenticity. This adversarial zero-sum game results in highly realistic generative outputs.

Synthetic Data Generation

Leverage advanced GAN architectures natively integrated into M1.