Contrastive Hebbian learning explained

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

• Oja's rule
• Generalized Hebbian algorithm

Notes and References

1. Qiu. Yixuan. Zhang. Lingsong. Wang. Xiao. 2019-09-25. Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent Variable Models. en. presented at the International Conference on Learning Representations, 2019
2. Xie. Xiaohui. Seung. H. Sebastian. February 2003. Equivalence of backpropagation and contrastive Hebbian learning in a layered network. Neural Computation. 15. 2. 441–454. 10.1162/089976603762552988. 0899-7667. 12590814. 11201868 .