NIPS 2016 Tutorial: Generative Adversarial Networks

This report summarizes the tutorial presented by the author at NIPS 2016 on generative adversarial networks (GANs). The tutorial describes: (1) Why generative modeling is a topic worth studying, (2) how generative models work, and how GANs compare to other generative models, (3) the details of how GANs work, (4) research frontiers in GANs, and (5) state-of-the-art image models that combine GANs with other methods. Finally, the tutorial contains three exercises for readers to complete, and the solutions to these exercises. Introduction This report summarizes the content of the NIPS 2016 tutorial on generative adversarial networks (GANs) (Goodfellow et al., 2014b). The tutorial was designed primarily to ensure that it answered most of the questions asked by audience members ahead of time, in order to make sure that the tutorial would be as useful as possible to the audience. This tutorial is not intended to be a comprehensive review of the field of GANs; many excellent papers are not described here, simply because they were not relevant to answering the most frequent questions, and because the tutorial was delivered as a two hour oral presentation and did not have unlimited time cover all subjects. The tutorial describes: (1) Why generative modeling is a topic worth studying, (2) how generative models work, and how GANs compare to other generative models, (3) the details of how GANs work, (4) research frontiers in GANs, and (5) state-of-the-art image models that combine GANs with other methods. Finally, the tutorial contains three exercises for readers to complete, and the solutions to these exercises. The slides for the tutorial are available in PDF and Keynote format at the following URLs: http://www.iangoodfellow.com/slides/2016-12-04-NIPS.pdf 1This is the arxiv.org version of this tutorial. Some graphics have been compressed to respect arxiv.org’s 10MB limit on paper size, and do not reflect the full image quality. 1 ar X iv :1 70 1. 00 16 0v 4 [ cs .L G ] 3 A pr 2 01 7