Sleep prevents catastrophic forgetting in spiking neural networks by forming a joint synaptic weight representation

0564951 - ÚI 2023 RIV US eng J - Journal Article
Golden, R. - Delanois, J. E. - Šanda, Pavel - Bazhenov, M.
Sleep prevents catastrophic forgetting in spiking neural networks by forming a joint synaptic weight representation.
PLoS Computational Biology. Roč. 18, č. 11 (2022), č. článku e1010628. ISSN 1553-734X. E-ISSN 1553-7358
Institutional support: RVO:67985807
Keywords : spiking model * catastrophic forgetting * sleep
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 4.3, year: 2022
Method of publishing: Open access
https://dx.doi.org/10.1371/journal.pcbi.1010628

Artificial neural networks overwrite previously learned tasks when trained sequentially, a phenomenon known as catastrophic forgetting. In contrast, the brain learns continuously, and typically learns best when new training is interleaved with periods of sleep for memory consolidation. Here we used spiking network to study mechanisms behind catastrophic forgetting and the role of sleep in preventing it. The network could be trained to learn a complex foraging task but exhibited catastrophic forgetting when trained sequentially on different tasks. In synaptic weight space, new task training moved the synaptic weight configuration away from the manifold representing old task leading to forgetting. Interleaving new task training with periods of off-line reactivation, mimicking biological sleep, mitigated catastrophic forgetting by constraining the network synaptic weight state to the previously learned manifold, while allowing the weight configuration to converge towards the intersection of the manifolds representing old and new tasks. The study reveals a possible strategy of synaptic weights dynamics the brain applies during sleep to prevent forgetting and optimize learning.
Permanent Link: https://hdl.handle.net/11104/0336528