Statistical Analysis of an Autoassociative Memory Network

Abstract

A statistical method for analyzing the dynamic behavior of a synchronous autoassociative memory network is presented based on an extension of Amari-Maginu theory. Through computer simulations it is shown that when the memorized pattern ratio is small (r < 0.15) or large (r > 0.2), the derived theory shows good agreement.

Cite

Text

Fu. "Statistical Analysis of an Autoassociative Memory Network." Neural Computation, 1994. doi:10.1162/NECO.1994.6.5.837

Markdown

[Fu. "Statistical Analysis of an Autoassociative Memory Network." Neural Computation, 1994.](https://mlanthology.org/neco/1994/fu1994neco-statistical/) doi:10.1162/NECO.1994.6.5.837

BibTeX

@article{fu1994neco-statistical,
  title     = {{Statistical Analysis of an Autoassociative Memory Network}},
  author    = {Fu, Alan M. N.},
  journal   = {Neural Computation},
  year      = {1994},
  pages     = {837-841},
  doi       = {10.1162/NECO.1994.6.5.837},
  volume    = {6},
  url       = {https://mlanthology.org/neco/1994/fu1994neco-statistical/}
}