Portraits of Imaginary People explores the latent space of human faces by training a neural network to imagine and then depict portraits of people who do not exist. To do so, many thousands of photographs of faces taken from Flickr were fed to a type of machine-learning program called Generative Adversarial Network (GAN). GANs work by using two neural networks that play an adversarial game: one (the “Generator”) tries to generate an increasingly convincing output, while the second (the “Discriminator”) tries to learn to distinguish real photos from the artificially generated ones.
