Robust stability for stochastic interval delayed Hopfield neural networks

A type of stochastic interval delayed Hopfield neural networks as du(t) = [-AIu(t) WIf(t,u(t)) WIτf7τ(uτ(t)] dt σ(t, u(t), uτ(t)) dw(t) on t≥0 with initiated value u(s) = ζ(s) on - τ≤s≤0 has been studied. By using the Razumikhin theorem and Lyapunov functions, some sufficient conditions of their globally asymptotic robust stability and global exponential stability on such systems have been given. All the results obtained are generalizations of some recent ones reported in the literature for uncertain neural networks with constant delays or their certain cases.     

Stability analysis of cellular neural networks with time-varying delay

The global asymptotic stability of cellular neural networks with delays is investigated. Three kinds of time delays have been considered. New delay-dependent stability criteria are proposed and are formulated as the feasibility of some linear matrix inequalities, which can be checked easily by resorting to the recently developed interior-point algorithms. Based on the Finsler Lemma, it is theoretically proved that the proposed stability criteria are less conservative than some existing results.     

具有时滞的二阶Hopfield神经网络的稳定性分析

对具有时滞的二阶Hopfield型神经网络平衡点的全局渐近稳定性问题进行了研究。在不要求连接权矩阵的对称性和输入输出函数的可微性与单调性的情况下 ,通过构造适当的Lyapunov泛函得到了网络平衡点的存在性和全局渐近稳定性的若干充分条件 ,这些条件可用于设计全局渐近稳定的二阶人工神经网络。     

时滞细胞神经网络的全局渐近鲁棒稳定性分析

针对一类具有时滞的细胞神经网络系统,利用新的Lyapunov Krasovskii函数,给出了系统全局渐近鲁棒稳定的时滞相关稳定性条件。其结果以线性矩阵不等式的形式给出,可以很容易求出系统稳定的时滞上界。进而可以很容易得到时滞无关稳定性结果,且该结果包含了现有文献中许多关于时滞无关稳定性分析的结果。数值算例说明了结论的有效性。     

变时滞广义神经网络的指数稳定性

讨论具有可变时滞的Cohen Grossberg广义神经网络平衡态的稳定性问题。以推广的Halanay微分不等式为工具,通过构造合适的Lyapunov函数,结合Dini导数和不等式技巧,对具有可变时滞(适合于任何时滞有界情况)的广义神经网络平衡态的指数稳定性进行分析。在适当的假设条件下,得到了系统渐近指数稳定的几个充分性判据,与此同时也给出了相应的Lyapunov指数。     

Stability analysis of extended discrete-time BAMneural networks based on LMI approach

1 .INTRODUCTIONBidirectional associative memory model is a kind ofneural network models in common use with the abili-ty of information memory and association. Since thedistributed memory of the information,the networkcan associate a completed and clear mode stored in itfroman uncompleted and fuzzy mode . Bidirectionalassociative memory (BAM) proposed by B. KoskoinRef .[1] is a generalization of Cohen-Grossberg’smodel from single layer to two layers . Since then,there have beenlots of …     

Stability of stochastic switched epidemic systems with discrete or distributed time delay

Stochastic switched epidemic systems with a discrete or distributed time delay are constructed and investigated. By the Lyapunov method and lto＇s differential rule, the existence and uniqueness of global positive solution of each system is proved. And stability conditions of the disease-free equilibrium of the systems are obtained. Numerical simulations are presented to illustrate the results.     

Global exponential stability for delayed cellular neural networks and estimate of exponential convergence rate

Some sufficient conditions for the global exponential stability and lower bounds on the rate of exponential convergence of the cellular neural networks with delay (DCNNs) are obtained by means of a method based on delay differential inequality. The method, which does not make use of any Lyapunov functional, is simple and valid for the stability analysis of neural networks with delay. Some previously established results in this paper are shown to be special casses of the presented result.     

New results on the robust stability analysis of neural networks with discrete and distributed time delays

Delay-dependent robust stability of cellular neural networks with time-varying discrete and distributed time-varying delays is considered. Based on Lyapunov stability theory and the linear matrix inequality （LMIs） technique, delay-dependent stability criteria are derived in terms of LMIs avoiding bounding certain cross terms, which often leads to conservatism. The effectiveness of the proposed stability criteria and the improvement over the existing results are illustrated in the numerical examples.     

On the exponential stability of neural networks systems with time-varying delay

In this paper, exponential stability of Hopfield-type neural networks with time-varying delays are analyzed. By using the Lyapunov functional method, sufficient conditions are obtained for general exponential stabilities. At the same time, the output functions do not satisfy the Lipschitz conditions and do not require them to be differential or strictly monotonously increasing. Moreover, all results are established without assuming any symmetry of the connection matrix.A numeric example is pressented to show the effective of these criteria.     

Passivity analysis for uncertain stochastic neural networks with discrete interval and distributed time-varying delays

The problem of passivity analysis is investigated for uncertain stochastic neural networks with discrete interval and distributed time-varying delays. The parameter uncertainties are assumed to be norm bounded and the delay is assumed to be time-varying and belongs to a given interval, which means that the lower and upper bounds of interval time-varying delays are available. By constructing proper Lyapunov-Krasovskii functional and employing a combination of the free-weighting matrix method and stochastic analysis technique, new delay dependent passivity conditions are derived in terms of linear matrix inequalities (LMIs). Finally, numerical examples are given to show the less conservatism of the proposed conditions.     

Stability of stochastic neural networks with Markovian jumping parameters

The global asymptotical stability for a class of stochastic delayed neural networks (SDNNs) with new delay-dependent stability conditions are derived. All results are expressed in terms of linear matrix inequality (LMI), and a numerical example is presented to illustrate the correctness and less conservativeness of the proposed method.     

不同演化模式的离散Hopfield网络的稳定性研究

神经网络的稳定性被认为是神经网络应用的基础。研究了非对称离散Hopfield神经网络的异步、同步、部分同步演化方式的稳定性 ,证明得到对于已知稳定的网络 ,如果经其连接权矩阵一定的增量 ,得到一个新的连接权矩阵 ,则在一定条件下可保证所得新的网络仍是稳定的。所获结果不仅推广了已有的结论 ,而且为离散Hopfield神经网络稳定性的稳健性能分析和应用提供了理论基础。     

延迟离散Hopfield-型网络的收敛性及其算法

给出了延迟离散 Hopfield-型网络的收敛性定理 ,提出了用于组合优化计算的延迟扰动算法 .在正规异步运行规则下 ,证明了网络滞后于能量函数收敛的步数由 Hopfield结果的 n2 步降到 2 n +1步 .揭示了离散 Hopfield-型网络与延迟离散 Hopfield-型神经网络收敛性的内在关系 ,为离散Hopfield-型网络的应用研究构筑了新的框架.     

基于数值积分的离散过程神经网络算法及应用

为解决离散过程神经网络的训练问题,提出了两种基于数值积分的离散过程神经网络训练算法.分别采用三次样条积分和抛物插值积分直接处理离散样本和权值的时域聚合运算,采用梯度下降法实现网络参数的调整.以漫湾水电站的月径流数据预报为例,实验结果表明,两种算法性能接近,均优于基于正交基展开的过程神经网络.     

Stability of nonlinearly-perturbed systems with time varying delay using LMIs

This paper studies delay dependent robust stability and the stabilization problem of nonlinear perturbed systems with time varying delay. A new set of sufficient conditions for the stability of open as well as close loop systems are obtained in the sense of Lyapunov-Krasovskii. To reduce the conservatism, the work exploits the idea of splitting the delay interval into multiple equal regions so that less information on the time delay can be imposed to derive the results. The derived criterion not only improves the upper bounds of the time delay but also does not require the derivative of the delay to be known at prior. Easily testable sufficient criteria are presented in terms of linear matrix inequalities. It is shown that the derived conditions are very less conservative while comparing the maximum allowable upper bound of delay with the existing results in literature.     

时滞竞争神经网络的全局指数稳定性

对于不同时标的时变时滞竞争神经网络的网络模型,通过构造适当的Lyapunov函数,结合微分不等式分析,研究了时变时滞竞争神经网络的全局指数稳定性,获得了新的全局指数稳定性判据,所得判据推广和改进了前人的相关结论。最后的数值仿真例子证明了该算法的有效性。     

离散Hopfield神经网络的异步渐近行为

主要研究非对称离散Hopfield神经网络和带有延迟项的非对称离散Hopfield神经网络的异步渐近行为。提出了异步演化的网络状态图和网络状态图的洞的概念 ,研究了网络状态图的洞和神经网络的异步稳定性之间的关系。给出了非对称离散Hopfield网络的异步稳定条件和不稳定条件以及某些特殊情况下的网络状态图的结构。同时 ,也得到了非对称延迟离散Hopfield网络的异步收敛性条件。所获结果推广了一些已有的结论。     

Design of twodimensional digital filters using neural networks

1.INTRODUCTION Two dimensional(2D)digitalfilteringisoneofthe mostfundamentalandmostimportantprocessing techniquesindigitalimageprocessingandother2D digitalsignalprocessingfields.Comparedwiththe designofone dimensional(1D)digitalfilters,2D digitalfiltersusuallymustbedesignedtosatisfyboth thedesiredmagnitudeandphaseresponsesespecially forimageprocessingapplicationsbecausehumanvi sionsystemismuchmoresensitivethanhumanaudi torysystemtowaveformdistortioncausedbythe phaseresponseoftheapplied2D…     

基于连续型Hopfield神经网络的噪声字符识别

采用连续型Hopfield神经网络(CHNN)对噪声字符进行识别。此模型比离散型Hopfield神经网络(DHNN)和布尔神经网络(BNN)更易于硬件实现，且在信息处理的并行性和实时性等方面更接近实际生物神经网络的工作原理。仿真结果表明该方法可以有效地对噪声字符进行识别。