Creative Adversarial Networks for Art Generation with Ahmed Elgammal
Today we’re joined by Ahmed Elgammal, a professor in the department of computer science at Rutgers, and director of The Art and Artificial Intelligence Lab. Ahmed and I caught up to discuss his work on AICAN, a creative adversarial network that produces original portraits, trained with over 500 years of European canonical art. In our conversation, Ahmed details the origin of AICAN and work on the project, how complex the computational representations of the art actually are, and how he simplifies it. We also dig into the specifics of the training process, including the various types of art used, and the constraints applied to the model.