Contrastive Hebbian learning
From HandWiki
Short description: Biologically plausible form of Hebbian learning with power equivalent to backpropagation
Contrastive Hebbian learning is a biologically plausible form of Hebbian learning.
It is based on the contrastive divergence algorithm, which has been used to train a variety of energy-based latent variable models.[1]
In 2003, contrastive Hebbian learning was shown to be equivalent in power to the backpropagation algorithms commonly used in machine learning.[2]
See also
References
- ↑ Qiu, Yixuan; Zhang, Lingsong; Wang, Xiao (2019-09-25) (in en). Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent Variable Models. https://openreview.net/forum?id=r1eyceSYPr. presented at the International Conference on Learning Representations, 2019
- ↑ Xie, Xiaohui; Seung, H. Sebastian (February 2003). "Equivalence of backpropagation and contrastive Hebbian learning in a layered network". Neural Computation 15 (2): 441–454. doi:10.1162/089976603762552988. ISSN 0899-7667. PMID 12590814. https://pubmed.ncbi.nlm.nih.gov/12590814/.
 |  |
