Jump to content

Contrastive Hebbian learning

From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by The Anome (talk | contribs) at 17:36, 6 April 2021 ({{neuroscience-stub}}). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Contrastive Hebbian learning is a biologically plausible form of Hebbian learning. It has been shown to be equivalent in power to the backpropagation algorithms used in machine learning.[1]

References

  1. ^ Xie, Xiaohui; Seung, H. Sebastian (2003-02). "Equivalence of backpropagation and contrastive Hebbian learning in a layered network". Neural Computation. 15 (2): 441โ€“454. doi:10.1162/089976603762552988. ISSN 0899-7667. PMID 12590814. {{cite journal}}: Check date values in: |date= (help)


Template:Machine-learning-stub