Effect of normalized interconnect matrix on the performance of Hopfield neural network

Shaoping Bian, Jie Li, Kebin XuProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 1992 · DOI

Abstract

It is shown by theoretical analysis and numerical simulations that there are some senses of reduction of the convergence property when the multi-valued matrix is substituted by a normalized matrix. Also, an optical experimental implementation scheme of Hopfield neural network which uses a novel multi-valued synaptic interconnect matrix realized by a combined system of LCLV and CRT controlled by a microcomputer is proposed.
BibTeX
@inproceedings{bian1992effect,
  author = {Shaoping Bian and Jie Li and Kebin Xu},
  title = {{Effect of normalized interconnect matrix on the performance of Hopfield neural network}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {1992},
  doi = {10.1117/12.135120},
}

Loading related content...

Figure