摘要
本文得到了Hopfield连续联想记忆各记忆模式的吸引域及其中每一点趋向记忆模式的指数收敛速度的估计结果,它们可用来评价Hopfield连续反馈联想记忆的容错能力,且可用于综合更为实用的连续联想记忆神经网络。
Some results about estimation of the domain of attraction of memory patterns and exponential convergence rate of the network trajectories to memory patterns for Hopfield's continuous-time associative memory are obtained. These results can be used not only for evaluation of errorcorrection capability of Hopfield contimuous-time associative memories,but also for the synthesis of efficient continuous-time associative memory neural networks.
出处
《电子学报》
EI
CAS
CSCD
北大核心
1996年第1期40-43,共4页
Acta Electronica Sinica
基金
国家攀登计划和国家自然科学基金
关键词
神经网络
基本约束
吸引域
指数收敛速度
Neural networks,Fundamental constraints,Domain of attraction,Exponential convergence rate