ML Anthology

Covariance Learning of Correlated Patterns in Competitive Networks

Ali A. Minai
NeCo 1997 pp. 667-681
doi:10.1162/NECO.1997.9.3.667 /neco/1997/minai1997neco-covariance/

Abstract

Covariance learning is a powerful type of Hebbian learning, allowing both potentiation and depression of synaptic strength. It is used for associative memory in feedforward and recurrent neural network paradigms. This article describes a variant of covariance learning that works particularly well for correlated stimuli in feedforward networks with competitive K-of-N firing. The rule, which is nonlinear, has an intuitive mathematical interpretation, and simulations presented in this article demonstrate its utility.

NeCo Semantic Scholar

Cite

Text

Minai. "Covariance Learning of Correlated Patterns in Competitive Networks." Neural Computation, 1997. doi:10.1162/NECO.1997.9.3.667

Markdown

[Minai. "Covariance Learning of Correlated Patterns in Competitive Networks." Neural Computation, 1997.](https://mlanthology.org/neco/1997/minai1997neco-covariance/) doi:10.1162/NECO.1997.9.3.667

BibTeX

@article{minai1997neco-covariance,
  title     = {{Covariance Learning of Correlated Patterns in Competitive Networks}},
  author    = {Minai, Ali A.},
  journal   = {Neural Computation},
  year      = {1997},
  pages     = {667-681},
  doi       = {10.1162/NECO.1997.9.3.667},
  volume    = {9},
  url       = {https://mlanthology.org/neco/1997/minai1997neco-covariance/}
}