Mar 30 2018, 3:42pm
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,” stated the artistThe 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.”
Takes a s#!t on Ai Art
Published on Mar 16, 2018