This article originally appeared on VICE US.
Barrat, a recent high school graduate in West Virginia, made the images by feeding thousands of classical nude paintings scraped from WikiArt into a Generative Adversarial Network (GAN). The GAN uses a system of two neural networks called a “generator” and a “discriminator” to create convincing versions of the works using data from the paintings and machine learning.
When he previously tested this technique with landscape oil paintings, Barrat (who you might remember from his viral Kanye West neural network project) says the GAN was able to produce fairly convincing compositions with some surreal accents. In the nude portrait experiment, however, the neural network refused to move past its Dalí period.
“The GAN didn't successfully learn how to make realistic nude portraits,” the 18-year-old Barrat told me via email. “The discriminator part of the GAN isn't really able to tell the difference between blobs of flesh and humans, and once the generator realized it could keep feeding the discriminator blobs of flesh, and fool it this way, both networks just stopped learning how to paint more realistically.”
Though people might immediately recoil at these doughy beasts, Barrat hopes that people see the potential in art made with the assistance of AI. He said, “I believe that one of the next great art movements will be AI-created art. Just like how when the camera was introduced, art shifted from being focused on realism and accurate depictions of events to being more abstract and impressionistic.”
Barrat lives in San Francisco and has been working on AI projects with tech company Nvidia since he graduated from high school. He says he’ll soon be moving to work in a research lab at Stanford University, but he also hopes to one day attend art school.
Sign up for our newsletter to get the best of VICE delivered to your inbox daily.
Follow Peter Slattery on Twitter.