Let us look into their competing objectives: In this process, we can imagine two types agents: a criminal and cop. Let's take a theoretical example of the process of money counterfeiting. This kind of situation can be modeled in Game Theory as a minimax game. This relatively simple setup results in both of the agent's coming up with increasingly complex ways to deceive each other. At its core, a GAN includes two agents with competing objectives that work through opposing goals. The basic idea behind GANs is actually very simple.
The code for this blog can be found here. Visualizing and analyzing different aspects of the GAN to better understand what's happening behind the scenes.Implementing a GAN-based model that generates data from a simple distribution.Basic idea and intuition behind workings of Generative Adversarial Networks.This post is broken down in following way: In this blog, we will build out the basic intuition of GANs through a concrete example. Generative Adversarial Networks or GANs are one of the most active areas in deep learning research and development due to their incredible ability to generate synthetic results.