So, we've seen the different structures and types of GANs. We know that GANs can be used for a variety of tasks. But, what does a GAN actually output? Similar to the structure of a neural network (deep or otherwise), we can expect that the GAN will be able to output any value that a neural network can produce. This can take the form of a value, an image, or many other types of variables. Nowadays, we usually use the GAN architecture to apply and modify images.