PoliBa-Courses/Deep-Learning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added new footnote

Browse Source
This commit is contained in:
Christian Risi 2025-04-20 11:59:07 +02:00
parent 2ddb65b09b
commit 0dbb35b43a
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Chapters/5-Optimization/Fancy-Methods/ADAM.md
View File

@ -69,7 +69,7 @@ Usual values are these:
- We need to - We need to
***tune 2 momentum parameters instead of 1*** ***tune 2 momentum parameters instead of 1***
## Notes[^anelli-adam-3] ## Notes[^anelli-adam-3][^adamw-notes]
- Whenever the ***gradient*** is constant, the `local - Whenever the ***gradient*** is constant, the `local
gain` is 1, as gain` is 1, as
@ -97,3 +97,5 @@ Usual values are these:
[^anelli-adam-2]: Vito Walter Anelli | Deep Learning Material 2024/2025 | PDF 5 pg. 54 [^anelli-adam-2]: Vito Walter Anelli | Deep Learning Material 2024/2025 | PDF 5 pg. 54
[^anelli-adam-3]: Vito Walter Anelli | Deep Learning Material 2024/2025 | PDF 5 pg. 57-58 [^anelli-adam-3]: Vito Walter Anelli | Deep Learning Material 2024/2025 | PDF 5 pg. 57-58
[^adamw-notes]: [AdamW Notes](./ADAM-W.md)