Imagine an algorithm, that can generate human face and algorithm, that can measure how good that face is. Now set two generating algorithm against each other and set measuring algorithm as a jury. Now after each generation opposing algorithm will try better, until some precision will be reached. And that’s why GAN is good at generating.
Bonus part: [https://www.nvidia.com/en-us/research/ai-playground/](https://www.nvidia.com/en-us/research/ai-playground/)
Latest Answers