Biblio Discovery — Demo Discovery Service

1 results for "Timo Flesch"

Showing 1–1 · 0.51 seconds · RSS

  1. Journal Article Full text

    Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals

    Timo Flesch; David G. Nagy; Andrew Saxe et al.

    PLOS Computational Biology, Vol. 19 No. 1 · 2023 · English · PLOS Scopus

    Humans can learn several tasks in succession with minimal mutual interference but perform more poorly when trained on multiple tasks at once. The opposite is true for standard deep neural networks. Here, we propose novel computational constraints for artificial neural networks, inspired by earlier…