←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: 0.734s | source
Show context
itsthecourier ◴[14 Apr 25 03:01 UTC] No.43677688[source]▶
"Whenever these kind of papers come out I skim it looking for where they actually do backprop.

Check the pseudo code of their algorithms.

"Update using gradient based optimizations""

replies(4): >>43677717 #>>43677878 #>>43684074 #>>43725019 #
1. arrakark ◴[14 Apr 25 03:08 UTC] No.43677717[source]▶
Same.

If I had to guess it's just local gradients, not an end-to-end gradient.