###
DOI:
Journal of Software:1994.5(8):9-13

PLN网络吸引区域的定量分析
张铃,张钹
(安徽大学计算机系,合肥 230039;清华大学计算机系,杭州 310027;浙江大学计算机系,北京 100084;清华大学智能技术与系统实验室,北京 100084)
THE QUANTITATIVE ANALYSIS OF THE ATTRACTIVE REGION OF THE PLN NETWORK
Zhang Ling,Zhang Bo
()
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 2586   Download 3105
Received:March 04, 1994    Revised:April 19, 1994
> 中文摘要: 本文证明在PLN网络中适当给定广义A-学习律,可使网络满足如下条件:(1)所有训练样本都是稳定状态;(2)每个稳定状态具有最大的吸引域;(3)具有很快的收敛速度.由此可见,将这种PLN网络作为联想记忆器是很理想的.
Abstract:This paper shows that when a generalized A-learning rule of a PLN net is given properly, the net can satisfy the following conditions. (1) All training samples are itsstable states. (2) Each stable state has a maximal attractive region. (3) The net has veryfast convergence speed. Therefore, as an associative memory the PLN network is an idealone.
文章编号:     中图分类号:    文献标志码:
基金项目:国家攀登计划,863高科技支持 国家攀登计划,863高科技支持
Foundation items:
Reference text:

张铃,张钹.PLN网络吸引区域的定量分析.软件学报,1994,5(8):9-13

Zhang Ling,Zhang Bo.THE QUANTITATIVE ANALYSIS OF THE ATTRACTIVE REGION OF THE PLN NETWORK.Journal of Software,1994,5(8):9-13