←back to thread

NoProp: Training neural networks without back-propagation or forward-propagation

(arxiv.org)
161 points belleville | 1 comments | 14 Apr 25 00:03 UTC | HN request time: 0.337s | source
Show context
erikerikson ◴[14 Apr 25 04:28 UTC] No.43678060[source]▶
We have gradient free algorithms: Hebbian learning. Since 1949?
replies(2): >>43678480 #>>43680305 #
1. uoaei ◴[14 Apr 25 06:02 UTC] No.43678480[source]▶
And there's good reasons why we use gradients today.