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. In my conversation with Ahmed, we discuss:
• His work on AICAN, a creative adversarial network that produces original portraits, trained with over 500 years of European canonical art.
• How complex the computational representations of the art actually are, and how he simplifies them.
• Specifics of the training process, including the various types of artwork used, and the constraints applied to the model.