摘要
本文讨论将单层反馈PLN(概率逻辑神经元模型)网络当作联想记忆网络时,其识别的复杂性问题,即其平均识别速度与网络规模之间的数量关系,我们得到的主要结论是,设单层反馈PLN网络N的规模为m,则其识别计算量是m的指数函数,给出识别计算量是m多项式的必要条件。
Regarding a single-layered PLN network with feedback connections as an associative memory network,the complexity of recognition is discussed.The main result is : if the size of the network N is m,then the complexity of recognition is an exponential function of m.The necessary condition in which the complexity is polynomial is given.
出处
《计算机学报》
EI
CSCD
北大核心
1993年第5期321-326,共6页
Chinese Journal of Computers
关键词
PLN网络
单层反馈
识别
复杂性
PLN network,stable state,associative memory network,Markov chain,transition matrix,the complexity of recognition.
