English

Synaptic metaplasticity in binarized neural networks

Neural and Evolutionary Computing 2021-06-09 v1

Abstract

Unlike the brain, artificial neural networks, including state-of-the-art deep neural networks for computer vision, are subject to "catastrophic forgetting": they rapidly forget the previous task when trained on a new one. Neuroscience suggests that biological synapses avoid this issue through the process of synaptic consolidation and metaplasticity: the plasticity itself changes upon repeated synaptic events. In this work, we show that this concept of metaplasticity can be transferred to a particular type of deep neural networks, binarized neural networks, to reduce catastrophic forgetting.

Keywords

Cite

@article{arxiv.2101.07592,
  title  = {Synaptic metaplasticity in binarized neural networks},
  author = {Axel Laborieux and Maxence Ernoult and Tifenn Hirtzlin and Damien Querlioz},
  journal= {arXiv preprint arXiv:2101.07592},
  year   = {2021}
}

Comments

3 pages, 1 figure

R2 v1 2026-06-23T22:18:45.854Z