首页 | 官方网站   微博 | 高级检索  
     

形态学联想记忆存储性能的研究
引用本文:冯乃勤,王善侠,敖连辉,徐久成,张新明.形态学联想记忆存储性能的研究[J].计算机工程与应用,2011,47(21):39-42.
作者姓名:冯乃勤  王善侠  敖连辉  徐久成  张新明
作者单位:河南师范大学计算机与信息技术学院,河南新乡,453007
基金项目:国家自然科学基金,河南省自然科学基金,河南师范大学博士基金
摘    要:形态学联想记忆(Morphological Associative Memories,MAM)的存储性能是衡量形态学联想记忆能力大小的重要指标。然而,迄今为止,对形态学联想记忆的存储性能,主要是对异联想形态学联想记忆(hetero-MAM)的存储性能的定量分析和定性刻画并未完成。这是一个悬而未决的理论问题,也是一个MAM应用的实际问题。针对这一问题开展研究,站在概率论的角度,提出一个MAM存储性能的概率模型,并进行了证明。通过定量分析和定性讨论,取得一致结论。研究和分析表明,het-ero-MAM的存储性能受到输入模式向量维数n、输出模式向量维数m、以及输入、输出模式对数目K的影响,且三者的影响程度不同。提出的概率模型,对形态学联想记忆的研究、分析、设计和应用,具有一定的启发和帮助。

关 键 词:形态学联想记忆  存储性能  概率模型
修稿时间: 

Research on recall performance of morphological associative memories
FENG Naiqin,WANG Shanxia,AO Lianhui,XU Jiucheng,ZHANG Xinming.Research on recall performance of morphological associative memories[J].Computer Engineering and Applications,2011,47(21):39-42.
Authors:FENG Naiqin  WANG Shanxia  AO Lianhui  XU Jiucheng  ZHANG Xinming
Affiliation:School of Computer and Information Technology,Henan Normal University,Xinxiang,Henan 453007,China
Abstract:The recall performance of Morphological Associative Memories(MAM) is an important criterion for judging the recall capacity of MAM.However,up to the present,for the recall performance of MAM,mainly for hetero-MAM,it has not been depicted quantitatively and not been analyzed qualitatively.It is an unsolved theoretical problem,and also a practical problem in applications.This paper focuses on the problem.A probability model of the recall performance of MAM is presented and proved,by using the probability method.Some consistent and significant conclusions are obtained through quantitative analysis and qualitative discussion.The research and analysis show that the input vector's dimension n,the output vector's dimension m,and the K,the number of pairs of input and output models,will influence the recall performance of MAM,and their influence to the recall performance is different.The probability model has some heuristic function and help significance for the research,analysis,design and application of MAM.
Keywords:morphological associative memories  recall performance  probability model
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载全文
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-23

京公网安备 11010802026262号