Many machine learning systems look at some kind of complicated input (say, an image) and produce a simple output (a label like, "cat"). By contrast, the goal of a generative model is something like the opposite: take a small piece of input—perhaps a few random numbers—and produce a complex output, like an image of a realistic-looking face. A generative adversarial network (GAN) is an especially effective type of generative model, introduced only a few years ago, which has been a subject of intense interest in the machine learning community.

You might wonder why we want a system that produces realistic images, or plausible simulations of any other kind of data. Besides the intrinsic intellectual challenge, this turns out to be a surprisingly handy tool, with applications ranging from art to enhancing blurry images.