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...
Spremljeno u:
| Glavni autori: | , |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
Springer
2024-11-01
|
| Serija: | Complex & Intelligent Systems |
| Teme: | |
| Online pristup: | https://doi.org/10.1007/s40747-024-01607-9 |
| Oznake: |
Bez oznaka, Budi prvi tko označuje ovaj zapis!
|