期刊文献+
共找到119篇文章
< 1 2 6 >
每页显示 20 50 100
GLOBAL DYNAMICS OF DELAYED BIDIRECTIONAL ASSOCIATIVE MEMORY (BAM) NEURAL NETWORKS
1
作者 周进 刘曾荣 向兰 《Applied Mathematics and Mechanics(English Edition)》 SCIE EI 2005年第3期327-335,共9页
Without assuming the smoothness,monotonicity and boundedness of the activation functions, some novel criteria on the existence and global exponential stability of equilibrium point for delayed bidirectional associativ... Without assuming the smoothness,monotonicity and boundedness of the activation functions, some novel criteria on the existence and global exponential stability of equilibrium point for delayed bidirectional associative memory (BAM) neural networks are established by applying the Liapunov functional methods and matrix_algebraic techniques. It is shown that the new conditions presented in terms of a nonsingular M matrix described by the networks parameters,the connection matrix and the Lipschitz constant of the activation functions,are not only simple and practical,but also easier to check and less conservative than those imposed by similar results in recent literature. 展开更多
关键词 bidirectional associative memory (bam) neural network global exponential stability Liapunov function
下载PDF
A NEW BIDIRECTIONAL ASSOCIATIVE MEMORY MODEL-HOMIBAM
2
作者 王保云 杨绿溪 何振亚 《Journal of Electronics(China)》 1995年第4期325-329,共5页
A new bidirectional associative memory model named as HOMIBAM is introduced. The relationships of HOMIBAM with the models existed are pointed out. Both theoretical analysis and simulations show that the capacity and r... A new bidirectional associative memory model named as HOMIBAM is introduced. The relationships of HOMIBAM with the models existed are pointed out. Both theoretical analysis and simulations show that the capacity and recall performance of HOMIBAM are superior to that of modified intraconnected BAM (MIBAM), higher-order BAM (HOBAM ) greatly. 展开更多
关键词 bidirectional associative memory RECALL Capacity Pattern PAIR Intraconnec-tion HIGHER-ORDER Error-correcting capability
下载PDF
DISCRETE BIDIRECTIONAL ASSOCIATIVE MEMORY WITH LEARNING FUNCTION
3
作者 王正欧 魏清刚 王红晔 《Transactions of Tianjin University》 EI CAS 1999年第1期25-30,共6页
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 opti... 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. 展开更多
关键词 bidirectional associative memory cross inhibitory connections optimal associative mapping nonlinear function stability of network memory capacity noise suppression
下载PDF
BIDIRECTIONAL ASSOCIATIVE MEMORY ENSEMBLE
4
作者 王敏 储荣 《Transactions of Nanjing University of Aeronautics and Astronautics》 EI 2007年第4期343-348,共6页
The multiple classifier system (MCS), composed of multiple diverse classifiers or feed-forward neural networks, can significantly improve the classification or generalization ability of a single classifier. Enlighte... The multiple classifier system (MCS), composed of multiple diverse classifiers or feed-forward neural networks, can significantly improve the classification or generalization ability of a single classifier. Enlightened by the fundamental idea of MCS, the ensemble is introduced into the quick learning for bidirectional associative memory (QLBAM) to construct a BAM ensemble, for improving the storage capacity and the error-correction capability without destroying the simple structure of the component BAM. Simulations show that, with an appropriate "overproduce and choose" strategy or "thinning" algorithm, the proposed BAM ensemble significantly outperforms the single QLBAM in both storage capacity and noise-tolerance capability. 展开更多
关键词 bidirectional associative memory neural network ensemble thinning algorithm
下载PDF
A UNIFIED BIDIRECTIONAL ASSOCIATIVEMEMORY MODEL
5
作者 王保云 周洪祥 +1 位作者 杨绿溪 何振亚 《Journal of Southeast University(English Edition)》 EI CAS 1995年第2期32-36,共5页
A unified bidirectional associative memory model (UBAM) isproposed- Its two special cases, UHOBAM and UEBAM, are the modifica-tions of intraconnected BAM (IBAM) and higher-order BAM (HOBAM),exponential BAM (EBAM) and ... A unified bidirectional associative memory model (UBAM) isproposed- Its two special cases, UHOBAM and UEBAM, are the modifica-tions of intraconnected BAM (IBAM) and higher-order BAM (HOBAM),exponential BAM (EBAM) and modified exponential BAM (MEBAM) , re- 展开更多
关键词 bidirectional associative memory pattern PAIR capacity error-correcting capability RECALL SIGNAL-TO-NOISE analysis
下载PDF
SOME STATISTICAL ANALYSIS OF THE RECALL PROBABILITY OF PARALLEL INTRACONNECTED BIDIRECTIONAL ASSOCIATIVE MEMORY
6
作者 Wang Baoyun Yang Luxi Lu Hongtao He Zhenya(Depart, of Radio Eng., Southeast Univ., Nanjing 210096) 《Journal of Electronics(China)》 1996年第1期17-22,共6页
This paper addressed a statistical analysis for the recall of parallel intraconnected bidirectional associative memory-Modified Intraconnected Bidirectional Associative Memory (MIBAM) and proved the conclusions: two M... This paper addressed a statistical analysis for the recall of parallel intraconnected bidirectional associative memory-Modified Intraconnected Bidirectional Associative Memory (MIBAM) and proved the conclusions: two MIBAM with the equal total number of neurons have the equal recalling probability for m pairs of stored pattern pairs if m is not too large. So they have the same capacity and same error correcting ability, i. e., their performances are statistically equivalent. The results of simulation support the conclusions well. 展开更多
关键词 bidirectional associative memory Capacity Recalling PROBABILITY
下载PDF
GLOBAL EXPONENTIAL STABILITY IN HOPFIELD AND BIDIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORKS WITH TIME DELAYS 被引量:5
7
作者 RONGLIBIN LUWENLIAN CHENTIANPING 《Chinese Annals of Mathematics,Series B》 SCIE CSCD 2004年第2期255-262,共8页
Without assuming the boundedness, strict monotonicity and differentiability of the activation functions, the authors utilize the Lyapunov functional method to analyze the global convergence of some delayed models. For... Without assuming the boundedness, strict monotonicity and differentiability of the activation functions, the authors utilize the Lyapunov functional method to analyze the global convergence of some delayed models. For the Hopfield neural network with time delays, a new sufficient condition ensuring the existence, uniqueness and global exponential stability of the equilibrium point is derived. This criterion concerning the signs of entries in the connection matrix imposes constraints on the feedback matrix independently of the delay parameters. From a new viewpoint, the bidirectional associative memory neural network with time delays is investigated and a new global exponential stability result is given. 展开更多
关键词 Hopfield neural network bidirectional associative memory (bam) Global exponential stability Time delays Lyapunov functional
原文传递
Global stability of bidirectional associative memory neural networks with continuously distributed delays 被引量:5
8
作者 张强 马润年 许进 《Science in China(Series F)》 2003年第5期327-334,共8页
Global asymptotic stability of the equilibrium point of bidirectional associative memory (BAM) neural networks with continuously distributed delays is studied. Under two mild assumptions on the activation functions, t... Global asymptotic stability of the equilibrium point of bidirectional associative memory (BAM) neural networks with continuously distributed delays is studied. Under two mild assumptions on the activation functions, two sufficient conditions ensuring global stability of such networks are derived by utilizing Lyapunov functional and some inequality analysis technique. The results here extend some previous results. A numerical example is given showing the validity of our method. 展开更多
关键词 global asymptotic stability bidirectional associative memory neural networks continuously distributed delays.
原文传递
New results on impulsive type inertial bidirectional associative memory neural networks 被引量:1
9
作者 Chaouki AOUITI Mahjouba Ben REZEG Yang CAO 《Frontiers of Information Technology & Electronic Engineering》 SCIE EI CSCD 2020年第2期324-339,共16页
This paper is concerned with inertial bidirectional associative memory neural networks with mixed delays and impulsive effects.New and practical conditions are given to study the existence,uniqueness,and global expone... This paper is concerned with inertial bidirectional associative memory neural networks with mixed delays and impulsive effects.New and practical conditions are given to study the existence,uniqueness,and global exponential stability of anti-periodic solutions for the suggested system.We use differential inequality techniques to prove our main results.Finally,we give an illustrative example to demonstrate the effectiveness of our new results. 展开更多
关键词 Inertial neural networks Anti-periodic solutions Global exponential stability Impulsive effect Time-varying delay bidirectional associative memory
原文传递
故障树和BAM神经网络在光伏并网故障诊断中的应用 被引量:27
10
作者 李练兵 张秀云 +1 位作者 王志华 王志强 《电工技术学报》 EI CSCD 北大核心 2015年第2期248-254,共7页
介绍了光伏并网发电系统的主要故障模式及故障原因,以及故障树(FT)的理论和双向联想记忆(BAM)神经网络的结构与学习算法。针对光伏并网系统工作过程中可能出现的故障,提出一种将故障树和双向联想记忆神经网络融合在一起的故障诊断方法... 介绍了光伏并网发电系统的主要故障模式及故障原因,以及故障树(FT)的理论和双向联想记忆(BAM)神经网络的结构与学习算法。针对光伏并网系统工作过程中可能出现的故障,提出一种将故障树和双向联想记忆神经网络融合在一起的故障诊断方法。通过故障树分析法(FTA)得到系统的所有故障模式,然后再由故障模式和根据维修经验的故障分析归纳出BAM的学习样本,即故障模式与故障分析之间的对应。通过光伏系统故障诊断的实验与应用,结果表明,该方法具有很好的实时性和有效性。 展开更多
关键词 故障树 双向联想记忆神经网络 故障诊断
下载PDF
具有时滞的双向联想记忆(BAM)的神经网络的全局动力学行为 被引量:7
11
作者 周进 刘曾荣 向兰 《应用数学和力学》 EI CSCD 北大核心 2005年第3期300-308,共9页
 在没有假定关联函数的光滑性,单调性和有界性的条件下,应用Liapunov泛函方法和矩阵代数技术,得到具有常数传输时滞的双向联想记忆(BAM)的神经网络模型平衡点存在性和全局指数稳定性的一些新的充分条件,这些条件可以由网络参数,连接矩...  在没有假定关联函数的光滑性,单调性和有界性的条件下,应用Liapunov泛函方法和矩阵代数技术,得到具有常数传输时滞的双向联想记忆(BAM)的神经网络模型平衡点存在性和全局指数稳定性的一些新的充分条件,这些条件可以由网络参数,连接矩阵和关联函数的Lipschitz常数所表示的M矩阵来刻化· 这些结果不仅是简单和实用的。 展开更多
关键词 双向联想记忆(bam) 神经网络 全局指数稳定 LIAPUNOV泛函
下载PDF
EXPONENTIAL STABILITY AND PERIODIC SOLUTION OF HYBRID BIDIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORKS WITH DISCRETE DELAYS
12
作者 谢惠琴 王全义 《Annals of Differential Equations》 2004年第3期312-320,共9页
In this paper, we study the existence, uniqueness, and the global exponential stability of the periodic solution and equilibrium of hybrid bidirectional associative memory neural networks with discrete delays. By inge... In this paper, we study the existence, uniqueness, and the global exponential stability of the periodic solution and equilibrium of hybrid bidirectional associative memory neural networks with discrete delays. By ingeniously importing real parameters di > 0 (i = 1,2, …, n) which can be adjusted, making use of the Lyapunov functional method and some analysis techniques, some new sufficient conditions are established. Our results generalize and improve the related results in [9]. These conditions can be used both to design globally exponentially stable and periodical oscillatory hybrid bidirectional associative neural networks with discrete delays, and to enlarge the area of designing neural networks. Our work has important significance in related theory and its application. 展开更多
关键词 hybrid bidirectional associative memory neural networks periodic solution EQUILIBRIUM global exponential stability
原文传递
不确定时滞BAM神经网络的鲁棒稳定性 被引量:3
13
作者 冯伟 吴海霞 张伟 《计算机工程与应用》 CSCD 北大核心 2009年第8期36-38,共3页
利用自由权值矩阵和不等式分析技巧,研究了一类不确定时滞BAM神经网络的鲁棒稳定性问题。通过构造适当的Lya-punov泛函,对于所有允许的不确定性,以线性矩阵不等式形式给出了时滞BAM神经网络的全局鲁棒稳定性判据,该判据能够利用Matlab的... 利用自由权值矩阵和不等式分析技巧,研究了一类不确定时滞BAM神经网络的鲁棒稳定性问题。通过构造适当的Lya-punov泛函,对于所有允许的不确定性,以线性矩阵不等式形式给出了时滞BAM神经网络的全局鲁棒稳定性判据,该判据能够利用Matlab的LMI工具箱很容易地进行检验。此外,仿真示例进一步证明了判据的有效性。 展开更多
关键词 鲁棒稳定性 不确定双向联想记忆神经网络 变时滞 线性矩阵不等式
下载PDF
一种融合FTA与BAM的故障诊断方法 被引量:4
14
作者 苗伟 范波 +1 位作者 王新勇 马建伟 《微电子学与计算机》 CSCD 北大核心 2010年第6期60-63,共4页
在研究故障树分析(FTA)和双向联想记忆(BAM)神经网络在故障诊断中应用的基础上,提出了一种融合FTA和BAM的故障诊断方法.故障树存贮了系统关于顶事件发生的全部知识,利用FTA得到系统所有的故障模式,进而归纳出BAM的学习样本,即故障树中... 在研究故障树分析(FTA)和双向联想记忆(BAM)神经网络在故障诊断中应用的基础上,提出了一种融合FTA和BAM的故障诊断方法.故障树存贮了系统关于顶事件发生的全部知识,利用FTA得到系统所有的故障模式,进而归纳出BAM的学习样本,即故障树中故障现象(监测点状态组合)和底事件发生与否之间的对应.BAM通过联想记忆矩阵并行联想,得到诊断结果,扩展综合故障诊断能力.仿真结果表明该方法用于解决此类问题是有效的. 展开更多
关键词 故障树分析 bam神经网络 故障诊断
下载PDF
采用变频器故障树为训练样本的BAM神经网络故障诊断方法 被引量:7
15
作者 王新勇 陈涛 《电光与控制》 北大核心 2011年第5期85-89,96,共6页
研究故障树分析(FTA)和双向联想记忆(BAM)神经网络在故障诊断中的应用,提出了一种融合FTA和BAM的故障诊断方法。利用FTA得到系统所有的故障模式,进而由故障模式和根据维修经验的故障分析归纳出BAM的学习样本,即故障模式和故障分析之间... 研究故障树分析(FTA)和双向联想记忆(BAM)神经网络在故障诊断中的应用,提出了一种融合FTA和BAM的故障诊断方法。利用FTA得到系统所有的故障模式,进而由故障模式和根据维修经验的故障分析归纳出BAM的学习样本,即故障模式和故障分析之间的对应。BAM通过联想记忆矩阵并行联想,得到诊断结果,扩展综合故障诊断能力。用上述方法对变频器故障诊断进行仿真分析,结果表明该方法用于解决变频器故障问题是有效的。 展开更多
关键词 故障诊断 故障树 bam神经网络 变频器
下载PDF
形式背景的BAM神经网络模型及模型上的概念生成 被引量:1
16
作者 曲开社 田永生 +1 位作者 翟岩慧 梁吉业 《计算机科学》 CSCD 北大核心 2009年第10期209-212,221,共5页
形式概念分析是近年来发展较为迅速的一种数据挖掘工具,它已被广泛地应用于机器学习、软件配置、信息获取等领域,而神经网络是基于模拟人脑的智能特点而发展起来的一门新兴学科。它们之间的融合将有利于智能控制、模式识别、知识处理等... 形式概念分析是近年来发展较为迅速的一种数据挖掘工具,它已被广泛地应用于机器学习、软件配置、信息获取等领域,而神经网络是基于模拟人脑的智能特点而发展起来的一门新兴学科。它们之间的融合将有利于智能控制、模式识别、知识处理等学科的进一步发展。通过对BAM神经网络的设定,建立了形式背景和NK-BAM神经网络之间的对应关系,论证了NK-BAM模型的稳定状态与形式背景的概念格的概念结点之间的对应,为概念分析和神经网络的进一步研究奠定了理论基础。同时给出了一个基于神经网络的概念生成算法,并通过实例验证了算法的有效性。 展开更多
关键词 形式概念分析 形式背景 概念格 神经网络 双向联想记忆
下载PDF
基于BAM的用户查询与网页匹配的研究 被引量:1
17
作者 邓波 杜亚军 王丽 《河北师范大学学报(自然科学版)》 CAS 北大核心 2007年第5期594-599,共6页
提出一个新匹配的策略使用更加精确和现实的概念以提高过去的基于关键词的匹配策略.根据从各个网页中提取的自然语义概念为每个网页建立1个概念格子.这样概念格由双向联想记忆存储器进行编码以区别于过去复杂概念格建立算法.然后提取这... 提出一个新匹配的策略使用更加精确和现实的概念以提高过去的基于关键词的匹配策略.根据从各个网页中提取的自然语义概念为每个网页建立1个概念格子.这样概念格由双向联想记忆存储器进行编码以区别于过去复杂概念格建立算法.然后提取这些形式概念中与查询的关键词相关的对象与属性进行匹配操作. 展开更多
关键词 信息检索 双向联想记忆存储器 形式概念分析
下载PDF
基于BAM和FTA在车长周视指挥镜系统故障诊断专家系统的应用研究 被引量:2
18
作者 李英顺 赵玉鑫 王占峰 《电子设计工程》 2016年第16期22-24,27,共4页
文中对车长周视指挥镜系统的故障进行了深入了解与研究,提出了一种基于BAM神经网络和FTA相结合的诊断方法,利用故障树分析法建立各个分系统的故障树,使用最小割集对系统进行分解,生成BAM神经网络的训练样本。设计出一种权值矩阵的方法,... 文中对车长周视指挥镜系统的故障进行了深入了解与研究,提出了一种基于BAM神经网络和FTA相结合的诊断方法,利用故障树分析法建立各个分系统的故障树,使用最小割集对系统进行分解,生成BAM神经网络的训练样本。设计出一种权值矩阵的方法,克服了BAM神经网络数据样本冗余的问题,提高了BAM神经网络的训练效率以及收敛速度。应用该方法对某型坦克的车长周视指挥镜系统进行故障诊断,结果表明:该系统能够对故障进行准确定位,提高了故障诊断效率。 展开更多
关键词 车长周视指挥镜系统 双向联想记忆神经网路 故障树分析法 故障诊断
下载PDF
具时滞离散和分布BAM神经网络的全局渐近稳定性 被引量:3
19
作者 丁丹军 《扬州大学学报(自然科学版)》 CAS CSCD 北大核心 2009年第4期1-5,共5页
研究一类同时具离散时滞和分布时滞的BAM(bidirectional associative memory)神经网络平衡点的全局渐近稳定性问题.所给BAM模型对激活函数做了扇形非线性条件假设,利用M矩阵理论,通过构造新的Lyapunov函数并利用一些分析技巧,获得具时... 研究一类同时具离散时滞和分布时滞的BAM(bidirectional associative memory)神经网络平衡点的全局渐近稳定性问题.所给BAM模型对激活函数做了扇形非线性条件假设,利用M矩阵理论,通过构造新的Lyapunov函数并利用一些分析技巧,获得具时滞离散和分布BAM神经网络的全局渐近稳定性的充分条件.数值例子说明了所得结果的有效性. 展开更多
关键词 bam神经网络 离散时滞 分布时滞 全局渐近稳定性 LYAPUNOV-KRASOVSKII函数
下载PDF
连续BAM神经网络的稳定性分析—LMI/BMI方法 被引量:1
20
作者 刘妹琴 《电路与系统学报》 CSCD 北大核心 2005年第3期52-57,共6页
对于连续双向联想记忆(BAM)神经网络的平衡点的稳定性问题,目前人们已经得到了很多富有意义的成果。本文提出一种新的神经网络模型-标准神经网络模型(SNNM),利用不同的Lyapunov泛函和S方法推导出基于线性/双线性矩阵不等式(LMI/BMI)的S... 对于连续双向联想记忆(BAM)神经网络的平衡点的稳定性问题,目前人们已经得到了很多富有意义的成果。本文提出一种新的神经网络模型-标准神经网络模型(SNNM),利用不同的Lyapunov泛函和S方法推导出基于线性/双线性矩阵不等式(LMI/BMI)的SNNM全局渐近稳定性和全局指数稳定性的充分条件。通过状态的线性变换,将连续BAM神经网络转化为SNNM,并利用有关SNNM的稳定性的一些结论,得到连续BAM神经网络平衡点的全局渐近稳定性和全局指数稳定性的充分条件,这些条件都以LMI或BMI形式给出,容易验证,保守性低。该方法扩展了以前的稳定性结果,同时也适用于其它类型的递归神经网络的稳定性分析。 展开更多
关键词 标准神经网络模型(SNNM) 双向联想记忆(bam) 线性/双线性矩阵不等式(LMI/BMI) 渐近稳定 指数稳定性
下载PDF
上一页 1 2 6 下一页 到第
使用帮助 返回顶部