Sleep prevents catastrophic forgetting in spiking neural networks by forming a joint synaptic weight representation, 2022, Golden et al

Discussion in 'Other health news and research' started by CRG, Nov 29, 2022.

  1. CRG

    CRG Senior Member (Voting Rights)

    Messages:
    1,857
    Location:
    UK
    Plos Computational Biology

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


    Ryan Golden, Jean Erik Delanois, Pavel Sanda, Maxim Bazhenov

    Abstract

    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.

    Open access: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010628
     

Share This Page