首页 | 本学科首页   官方微博 | 高级检索  
     

多粒度多对多联想记忆的一种实现模型
引用本文:于晓,杨国为,王晓艳.多粒度多对多联想记忆的一种实现模型[J].青岛大学学报(工程技术版),2009,24(4):12-18,24.
作者姓名:于晓  杨国为  王晓艳
作者单位:1. 青岛大学自动化工程学院,山东,青岛,266071
2. 青岛大学自动化工程学院,山东,青岛,266071;Department of Electrical and Computer Engineering,University of Illinois at Chicago,Chicago,IL 60607,U.S
基金项目:国家自然科学基金资助项目,国家"八六三"高技术研究发展计划项目,山东省自然科学基金资助项目,山东省科技攻关项目 
摘    要:现有的多模块多对多联想记忆模型结构复杂,不能够实现多粒度联想。在一对多联想模型基础上,加入项编码逻辑运算网络和粒度控制网络,提出了一种基于模式关联的多模块多对多联想记忆神经网络模型。实例表明,该模型可以实现模式的多对多联想记忆,且能够对输出模式进行粒度控制。从而实现了多粒度多对多联想记忆。

关 键 词:多粒度联想  多对多联想记忆  模式编码  人工神经网络

An Implementation Model for Multi-Granularity and Many-to-Many Associative Memory
YU Xiao,YANG Guo-wei,WANG Xiao-yan.An Implementation Model for Multi-Granularity and Many-to-Many Associative Memory[J].Journal of Qingdao University(Engineering & Technology Edition),2009,24(4):12-18,24.
Authors:YU Xiao  YANG Guo-wei  WANG Xiao-yan
Affiliation:YU Xiao, YANG Guo-wei, WANG Xiao-yan (1. School of Automation Engineering, Qingdao University, Qingdao 266071, China; 2. Departmental Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, IL 60607, U. S. )
Abstract:The structures of present and these models can not carry out associative memory model based on multimodule many to-many associative memory models are complex, the multi-granularity association. A kind of multimodule many-to-many incidence of patterns is proposed by use of introducing logic calculation network and granularity control network based on one-to-many associative memory model. Examples show that this model can achieve many-to-many associative memory and control the granularity of output patterns. Thus this model realizes multi-granularity and many-to-many associative memory.
Keywords:many granularity association  many-to-many associative memory  pattern coding  artificialneural network
本文献已被 维普 万方数据 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