arthur/artsite
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/artsite.git synced 2026-02-13 04:07:40 +01:00
Code Issues 1 Packages Projects Releases Wiki Activity

Move Detailed Report section before Authors section in dropout-reduces-underfitting.md

Browse Source 
Co-authored-by: ArthurDanjou <29738535+ArthurDanjou@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2025-12-24 22:13:41 +00:00
parent 2e73c26b12
commit 17f3d06acb
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
content/projects/dropout-reduces-underfitting.md
View File

@@ -139,6 +139,11 @@ According to the paper, you should observe:
- Early Dropout: Higher initial Loss, followed by a sharp drop after the switch_epoch, often reaching a lower minimum than Standard Dropout (reduction of underfitting). - Early Dropout: Higher initial Loss, followed by a sharp drop after the switch_epoch, often reaching a lower minimum than Standard Dropout (reduction of underfitting).
- Late Dropout: Rapid rise in accuracy at the start (potential overfitting), then stabilized by the activation of dropout. - Late Dropout: Rapid rise in accuracy at the start (potential overfitting), then stabilized by the activation of dropout.
## 📄 Detailed Report
<iframe src="/projects/dropout-reduces-underfitting.pdf" width="100%" height="1000px">
</iframe>
## 📝 Authors ## 📝 Authors
- [Arthur Danjou](https://github.com/ArthurDanjou) - [Arthur Danjou](https://github.com/ArthurDanjou)
@@ -148,9 +153,4 @@ According to the paper, you should observe:
- [Moritz Von Siemens](https://github.com/MoritzSiem) - [Moritz Von Siemens](https://github.com/MoritzSiem)
M.Sc. Statistical and Financial Engineering (ISF) - Data Science Track at Université Paris-Dauphine PSL M.Sc. Statistical and Financial Engineering (ISF) - Data Science Track at Université Paris-Dauphine PSL
Based on the work of Liu, Z., et al. (2023). Dropout Reduces Underfitting. Based on the work of Liu, Z., et al. (2023). Dropout Reduces Underfitting.
## 📄 Detailed Report
<iframe src="/projects/dropout-reduces-underfitting.pdf" width="100%" height="1000px">
</iframe>