https://rohanvarma.me/inputnormalization/
Downsides of the sigmiod activation and why you should center your inputs
Software Engineer @ Facebook
rohanvarma.me
'자연어 처리 과정' 카테고리의 다른 글
| Training with SAM optimizer (0) | 2023.02.10 |
|---|---|
| Flat minima VS Sharp minima (0) | 2023.01.26 |
| Contiguous는 도대체 뭘까? (0) | 2023.01.18 |
| Pruning이란? (0) | 2023.01.16 |
| What is Learning Rate Warmup? (1) | 2023.01.16 |
