Training of Physical Neural Networks — mentioned by SaberTail

Tue, 24 Mar 2026 18:22:59 GMT

The term I've heard for this sort of thing is "Physical Neural Networks" or "PNN"s. My impression is that one of the big things holding them back is that because we can't manufacture components to perfect tolerances, you can't train a single model and reuse it like you can with digital logic. Even if you can get close, every single circuit needs some amount of tuning. And we haven't worked out great ways to train them. There's a lot of research going on in this space though, because yeah, nature can solve certain mathematical problems more efficiently than digital systems. There's a decent…

Paper and discussion history. A mention is not an endorsement.

Training of Physical Neural Networks — HN submission

Wed, 10 Jul 2024 13:13:51 GMT

Training of Physical Neural Networks

142 points; 46 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Training of Physical Neural Networks · HackerPapers discussions

Training of Physical Neural Networks — mentioned by SaberTail

Training of Physical Neural Networks — HN submission