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