Sleep-like unsupervised replay reduces catastrophic forgetting in artificial neural networks
Timothy Tadros,
Giri P. Krishnan,
Ramyaa Ramyaa and
Maxim Bazhenov ()
Additional contact information
Timothy Tadros: University of California San Diego
Giri P. Krishnan: University of California San Diego
Ramyaa Ramyaa: New Mexico Tech
Maxim Bazhenov: University of California San Diego
Nature Communications, 2022, vol. 13, issue 1, 1-12
Abstract:
Abstract 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 recent and old conflicting memory traces. Here we tested the hypothesis that implementing a sleep-like phase in artificial neural networks can protect old memories during new training and alleviate catastrophic forgetting. Sleep was implemented as off-line training with local unsupervised Hebbian plasticity rules and noisy input. In an incremental learning framework, sleep was able to recover old tasks that were otherwise forgotten. Previously learned memories were replayed spontaneously during sleep, forming unique representations for each class of inputs. Representational sparseness and neuronal activity corresponding to the old tasks increased while new task related activity decreased. The study suggests that spontaneous replay simulating sleep-like dynamics can alleviate catastrophic forgetting in artificial neural networks.
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
https://www.nature.com/articles/s41467-022-34938-7 Abstract (text/html)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-34938-7
Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/
DOI: 10.1038/s41467-022-34938-7
Access Statistics for this article
Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie
More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().