Theoretical understanding of gradients of spike functions as boolean functions
Abstract Applying an error-backpropagation algorithm to spiking neural networks frequently needs to employ fictive derivatives of spike functions (popularly referred to as surrogate gradients) because the spike function is considered non-differentiable. The non-differentiability comes into play give...
Guardat en:
| Autors principals: | , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
Springer
2024-11-01
|
| Col·lecció: | Complex & Intelligent Systems |
| Matèries: | |
| Accés en línia: | https://doi.org/10.1007/s40747-024-01607-9 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|