
Episode 16: Yilun Du, MIT, on energy-based models, implicit functions, and modularity
Generally Intelligent
00:00
Is Pure Randomness the Same Thing or Different?
Tillio: A lot of pure randomness is very hard to predictb the same time. Some papers are saying that you can get somewhat close actually, to image devaluing performance using completely random imagese were also not completely random,. They are not real images, but you have spent a lot of time framtrizing, like how the image is generated. And then you alsoad all these ocmentations.
Transcript
Play full episode