Too Long; Didn't Read
Machine learning models can now generate new images based on what it has seen from an existing set of images. This type of architecture is called a generative adversarial network, or GAN. You can control your GAN's output based on the simplest type of knowledge you could provide it: hand-drawn sketches. This new method by Sheng-Yu Wang et al. from Carnegie Mellon University and. MIT called Sketch Your Own GAN can take an existing model, a new model, to generate images of cats.