约束最小平方联想存储器及性能比较  

CONSTRAINED LEAST SQUARES ASSOCIATIVE MEMORY AND ITS PERFORMANCE COMPARISON

作　　者：陈松灿[1] 高航[1] 

机构地区：[1]南京航空航天大学计算机系

出　　处：《计算机研究与发展》1998年第5期408-411,共4页Journal of Computer Research and Development

基　　金：国家"攀登计划"项目

摘　　要：鉴于Ｋｏｈｏｎｅｎ的最佳联想存储器对带噪输入会产生难以接受的联想误差，文中试图通过在Ｋｏｈｏｎｅｎ模型中引入对连接权阵的某种约束并进而优化，使修改后的Ｋｏｈｏｎｅｎ模型（ＣＬＳＡＭ）对带噪输入具有最小误差的联想．借助奇异值分解（ＳＶＤ）理论的分析和计算机模拟证实了ＣＬＳＡＭ的性能优越性．Considering the sensitivity of Kohonen optimal associative memory to inputs with noise,a constrained least squares associative memory (CLSAM) is presented by introducing the constraints to the connection weights of Kohonen associative memory and further optimizing the memory performance of the CLSAM so that the CLSAM has minimum associative error or noise.With the help of the singular value decomposition (SVD) approach and computer simulations,the better performance of the CLSAM is confirmed compared with Kohonen associative model.

关 键 词：约束 神经网络 联想存储器 存储器 

分 类 号：TP333[自动化与计算机技术—计算机系统结构]