首页 | 本学科首页   官方微博 | 高级检索  
     检索      

一种具有学习功能的离散双向联想记忆(英)
引用本文:王正欧,魏清刚,王红晔.一种具有学习功能的离散双向联想记忆(英)[J].天津大学学报(英文版),1999(1).
作者姓名:王正欧  魏清刚  王红晔
作者单位:天津大学系统工程研究所
摘    要:提出了一种基于连续的线性双向联想记忆(LBAM)的离散双向联想记忆(DBAM).DBAM双向地进行K。honen提出的最优联想映射.同作者已提出的LBAM和NBAM一样,DBAM可保证对所有已存储模式的回忆,并具有较现有其它BAM高得多的容量,还和NBAM一样具有对输出模式中噪声的强抑制能力,并因此大大减少了伪记忆.给出了对DBAM的推导并证明了其稳定性.还推导了DBAM的学习算法,该算法具有选代形式,使网络易于学习新模式同NBAM相比,DBAM易于用软件实现.

关 键 词:双向联想记忆  横向抑制联接  最优联想映射  非线性函数  网络的稳定性  记忆容量  噪声抑制

DISCRETE BIDIRECTIONAL ASSOCIATIVE MEMORY WITH LEARNING FUNCTION
WANG Zheng ou,WEI Qinggang, WANG Hongye.DISCRETE BIDIRECTIONAL ASSOCIATIVE MEMORY WITH LEARNING FUNCTION[J].Transactions of Tianjin University,1999(1).
Authors:WANG Zheng ou  WEI Qinggang  WANG Hongye
Abstract:In this paper we propose a new discrete bidirectional associative memory (DBAM) which is derived from our previous continuous linear bidirectional associative memory (LBAM). The DBAM performs bidirectionally the optimal associative mapping proposed by Kohonen. Like LBAM and NBAM proposed by one of the present authors,the present BAM ensures the guaranteed recall of all stored patterns,and possesses far higher capacity compared with other existing BAMs,and like NBAM, has the strong ability to suppress the noise occurring in the output patterns and therefore reduce largely the spurious patterns. The derivation of DBAM is given and the stability of DBAM is proved. We also derive a learning algorithm for DBAM,which has iterative form and make the network learn new patterns easily. Compared with NBAM the present BAM can be easily implemented by software.
Keywords:bidirectional associative memory  cross inhibitory connections  optimal associative mapping  nonlinear function  stability of network  memory capacity  noise suppression
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号