News for hackers. Stuff that matters.
Re:There Will Be a Scientific Theory of Deep Learning by hodgehog11 on Saturday April 25, 2026 @04:31AM (#47899736)
This absolutely was the crux of the (first) mystery, and I would argue that "deep learning theory" really only took off once it recognized this. There are other mysteries too, like the feasibility of transfer learning, neural scaling laws, and now more recently, in-context learning.

There are no comments on this comment yet.