Resumen de Al's genre-defying artworks win fans
Art historian Marian Mazzone and her colleagues at Rutgers University in New Jersey and Facebook's AI lab in California modified what's known as a generative adversarial network, pitting two neural nets against each other to get better and better outcomes. The general idea is that one of them creates a solution, the other judges it--and the algorithm loops until it attains the desired result. The team built a generator network that devised images to be scrutinized by a discriminator network, which had learned from analyzing 81,500 paintings to distinguish between images they would class as artworks and those they wouldn't--such as a photo or diagram. The discriminator had also learned to distinguish between styles of art, such as rococo or cubism. The twist is that the generator was primed to produce images that the discriminator recognizes as art, but that don't fall into existing styles.
