Ilya Sutskever explains the origins of deep learning
The Robot Brains Podcast
Isn't Supervised Learning Really Necessary?
i was really interested in unsuperviseden and for context, is the results that you spoke about earlier on about vision. All these results translation, they are all cases where you have somehow betraye a neuro letwork by presenting it with inputs and desired outputs. I found it very unsatisfying in my mind. It felt to me like there is no good mathematical basis for nsupervised learning at all. And after a lot of thinking, i developed the belief that actually, if you predict the next bit really well, you should have eligod an supernis a. Another interesting thing that now knows that unsupervised learning just works, but not that long ago this completely intractable
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
