Effect of normalized interconnect matrix on the performance of Hopfield neural network
Shaoping Bian, Jie Li, Kebin Xu · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1992
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.