New top story on Hacker News: AdamW and Super-convergence is now the fastest way to train neural nets
AdamW and Super-convergence is now the fastest way to train neural nets
241 by tim_sw | 26 comments on Hacker News.
241 by tim_sw | 26 comments on Hacker News.
New top story on Hacker News: AdamW and Super-convergence is now the fastest way to train neural nets
![New top story on Hacker News: AdamW and Super-convergence is now the fastest way to train neural nets]()
Reviewed by Latest USA Update
on
July 04, 2018
Rating:
No comments: