Generative adversarial networks (GANs) are neural networks that can create
completely new things. I recently created my own GAN, check it out here!
An explanation of how I built my own generative adversarial
network to create new Pokemon.
A GAN is made up of two neural networks. The generator creates new data based on what it is given, while the discriminator tries to tell the difference between real and fake data. This works for art, music, and even Pokemon!
Based on a lot of data, the generator tries to find common features in the data and create new data. The discriminator tries to find common features in the same data, and looks at real and fake data to determine which is which.
GANs have so many applications, and this isn't limited to Pokemon. They can be used to discover new drugs, create synthetic data, generate images (for those of us that want to avoid looking for high-quality images), and more!