Post
Yo Shavit @yonashav ยท Mar 13, 2023
  • From Twitter

If this interests you, you should read this paper. IMO the most in-depth proof that after sufficient training, NNs learn simple, parsimonious, highly-general rules, even in the absence of overwhelming data.

Recommended by 1 person
1 mention
Share on Twitter Repost
Replies
Reply
No replies yet