A Deterministic Collatz Sequence Initialization for Faster Convergence and Stable Neural Network Training
Deep neural networks have achieved state-of-the-art performance in tasks ranging from image classification to regression. However, their training dynamics remain highly sensitive to weight initialization. This is a fundamental factor that influences both convergence speed and model performance. Trad...
Na minha lista:
| Principais autores: | , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
IEEE
2025-01-01
|
| Colecção: | IEEE Access |
| Assuntos: | |
| Acesso em linha: | https://ieeexplore.ieee.org/document/11248903/ |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|