Sleep-like unsupervised replay reduces catastrophic forgetting in artificial neural networks
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.
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-12-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-022-34938-7 |