GANs, based on supervised learning and game theory, are just so darn elegant. The Grace Kelly of deep learning.
Pitting the generator and the discriminator against each other (where the generator tries to fool the discriminator into classifying its output as a real sample) is genius in its simplicity.
This report here gives a very good definition of them in Section 2, and creates a multi-task deep convolutional GAN to classify emotions from audio.
Or you can watch Ian Goodfellow describe his creation here.