PT  - JOURNAL ARTICLE
AU  - Ryan Golden
AU  - Jean Erik Delanois
AU  - Pavel Sanda
AU  - Maxim Bazhenov
TI  - Sleep prevents catastrophic forgetting in spiking neural networks by forming joint synaptic weight representations
AID  - 10.1101/688622
DP  - 2020 Jan 01
TA  - bioRxiv
PG  - 688622
4099  - http://biorxiv.org/content/early/2020/06/10/688622.short
4100  - http://biorxiv.org/content/early/2020/06/10/688622.full
AB  - 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 learning is interleaved with periods of sleep for memory consolidation. In this study, 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 multiple tasks. New task training moved the synaptic weight configuration away from the manifold representing old tasks leading to forgetting. Interleaving new task training with periods of off-line reactivation, mimicking biological sleep, mitigated catastrophic forgetting by pushing the synaptic weight configuration towards the intersection of the solution manifolds representing multiple tasks. The study reveals a possible strategy of synaptic weights dynamics the brain applies during sleep to prevent forgetting and optimize learning.Competing Interest StatementThe authors have declared no competing interest.