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.
In 2003, contrastive Hebbian learning was shown to be equivalent in power to the
backpropagation algorithms commonly used in
machine learning.
References
See also
*
Oja's rule
*
Generalized Hebbian algorithm
Hebbian theory
Artificial neural networks
{{computing-stub