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

多重训练BAM算法中强化系数的解析求取
引用本文:铁锦程,程君实.多重训练BAM算法中强化系数的解析求取[J].上海交通大学学报,1996,30(11):56-61.
作者姓名:铁锦程  程君实
作者单位:[1]上海交通大学自动化系 [2]上海交通大学信息存储研究中心
基金项目:国家教委跨世纪人才基金,上海市科学技术基金
摘    要:从BAM的能量函数出发推导出强化系数的解析解形式。在强化系数的作用下,BAM网将被强化矢量对存储在皮知矢量对为中心Hemming距离为1的邻域里的能量最小点,人而保证了该矢量对的正确联想。给出了根据此解析算式编制的算法和计算实例。

关 键 词:双向联想记忆  存储器  强化系统  解析解

An Explicit Solution to the Reinforcing Parameter in Multiple Training BAM Algorithm
Tie Jincheng, Xu Xiaoming, Liu Hui.An Explicit Solution to the Reinforcing Parameter in Multiple Training BAM Algorithm[J].Journal of Shanghai Jiaotong University,1996,30(11):56-61.
Authors:Tie Jincheng  Xu Xiaoming  Liu Hui
Institution:Tie Jincheng; Xu Xiaoming; Liu Hui(Department of Automation)Cheng Junshi(Information Research Storage Center)
Abstract:This paper mainly discusses the choice of the reinforcing parameter in multiple training BAM algorithm. Starting from the energy function of the BAM network, an explicit solution of the parameter is finally reached. With this parameter, the BAM network can store the corresponding training vector pair at the minimum energy point within the area of 1Hemming distance from the vector pair. Thus ensures the pair can be correctly recalled later. An algorithm based on the explicit solution and an example are also given.
Keywords:bidirectional associative memory (BAM)  neural network  Hemming distance  
本文献已被 CNKI 维普 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