Английская Википедия:Contrastive Hebbian learning

Материал из Онлайн справочника
Перейти к навигацииПерейти к поиску

Шаблон:Short description 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

Шаблон:Reflist

Шаблон:Hebbian learning


Шаблон:Neuroscience-stub Шаблон:Computing-stub

  1. Шаблон:Cite journal presented at the International Conference on Learning Representations, 2019
  2. Шаблон:Cite journal