Muon: An optimizer for hidden layers in neural networks (kellerjordan.github.io)

4 points by tbalsam 1y ago ↗ HN

0 comments

[ 3.1 ms ] story [ 6.5 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats