1. Fast and slow synaptic plasticity enables concurrent control and learning

    This article has 2 authors:
    1. Brendan A Bicknell
    2. Peter E Latham
    This article has been curated by 1 group:
    • Curated by eLife

      eLife Assessment

      This paper provides an important proposal for why learning can be much faster and more accurate if synapses have a fast component that immediately corrects errors, as well as a slower component that corrects behavior averaged over a longer timescale. It is convincingly shown that integrating these two learning timescales improves performance compared to classical strategies, particularly in terms of robustness and generalization when learning new target signals. However, the biological plausibility and justification for the proposed rapid learning mechanism require further elaboration and supporting mechanistic examples.

    Reviewed by eLife

    This article has 3 evaluationsAppears in 1 listLatest version Latest activity
Previous Page 82 of 301 Next