The math behind GANs (Generative Adversarial Networks)

A detailed understanding of the math behind original GANs including their limitations

1. Introduction

The Generative Adversarial Network (GAN) comprises of two models: a generative model G and a discriminative model D. The generative model can be considered as a counterfeiter who is trying to generate fake currency and use it without being caught, whereas the discriminative model is similar to police, trying to catch the fake currency. This…