| Autor: |
Timothy Tadros, Giri P. Krishnan, Ramyaa Ramyaa, Maxim Bazhenov |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
Nature Communications, Vol 13, Iss 1, Pp 1-12 (2022) |
| Druh dokumentu: |
article |
| ISSN: |
2041-1723 |
| DOI: |
10.1038/s41467-022-34938-7 |
| Popis: |
Artificial neural networks are known to perform well on recently learned tasks, at the same time forgetting previously learned ones. The authors propose an unsupervised sleep replay algorithm to recover old tasks synaptic connectivity that may have been damaged after new task training. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
Full text from SpringerLink