Creative Machine Learning
Ahmed discusses the distinction between failure and creativity in machine-generated art, emphasizing that true innovation arises from understanding aesthetic rules rather than merely imitating existing styles. He highlights how art history evolves gradually, suggesting that machines must extrapolate from this trajectory to create genuinely new works, rather than mixing past styles. The essence of machine creativity lies in its ability to constructively generate new aesthetics rather than emulate past failures.In this clip
From this podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Creative Adversarial Networks for Art Generation with Ahmed Elgammal - TWiML Talk #265
Related Questions