Cargando…
Sleep-like unsupervised replay reduces catastrophic forgetting in artificial neural networks
Artificial neural networks are known to suffer from catastrophic forgetting: when learning multiple tasks sequentially, they perform well on the most recent task at the expense of previously learned tasks. In the brain, sleep is known to play an important role in incremental learning by replaying re...
| Autores principales: | , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Nature Publishing Group UK
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9755223/ https://www.ncbi.nlm.nih.gov/pubmed/36522325 http://dx.doi.org/10.1038/s41467-022-34938-7 |