The News 360
New top story on Hacker News: No More Adam: Learning Rate Scaling at Initialization Is All You Need
No More Adam: Learning Rate Scaling at Initialization Is All You Need
14 by jinqueeny |
0 comments
on Hacker News.
No comments:
Post a Comment
Newer Post
Older Post
Home
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment