Synaptic metaplasticity in binarized neural networks
Deep neural networks usually rapidly forget the previously learned tasks while training new ones. Laborieux et al. propose a method for training binarized neural networks inspired by neuronal metaplasticity that allows to avoid catastrophic forgetting and is relevant for neuromorphic applications.
Na minha lista:
| Principais autores: | , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
Nature Portfolio
2021-05-01
|
| coleção: | Nature Communications |
| Acesso em linha: | https://doi.org/10.1038/s41467-021-22768-y |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|