(github.com)

31 points NetRunnerSu | 1 comments | 27 Jun 25 11:10 UTC | HN request time: 0.278s | source

Show context

upghost ◴[27 Jun 25 18:43 UTC] No.44399180[source]▶

This looks absolutely fantastic, please accept my meagre professional jealousy. I have long bemoaned manual hyperparam fiddling . I have on occasion dabbled with nonparametric ("genetic") methods of hyperparam tuning inspired by AutoML... but then you still have to manually tune the evolutionary hyperparams.

Finding a way to derive this from the gradients is amazing.

replies(1): >>44401290 #

1. NetRunnerSu ◴[27 Jun 25 23:42 UTC] No.44401290[source]▶

>>44399180 #

This is definitely not just another machine learning method. It comes from a complete cognitive science theory, rooted in a complete understanding of intelligence and consciousness.

https://github.com/dmf-archive/IPWT

↑

Show HN: PILF, The ultimate solution to catastrophic oblivion on AI models