Adaptive synchronization under almost every initial data for stochastic neural networks with time-varying delays and distributed delays

This paper is concerned with the adaptive synchronization problem for a class of stochastic delayed neural networks. Based on the LaSalle invariant principle of stochastic differential delay equations and the stochastic analysis theory as well as the adaptive feedback control technique, a linear matrix inequality approach is developed to derive some novel sufficient conditions achieving complete synchronization of unidirectionally coupled stochastic delayed neural networks. In particular, the synchronization criterion considered in this paper is the globally almost surely asymptotic stability of the error dynamical system, which has seldom been applied to investigate the synchronization problem. Moreover, the delays proposed in this paper are time-varying delays and distributed delays, which have rarely been used to study the synchronization problem for coupled stochastic delayed neural networks. Therefore, the results obtained in this paper are more general and useful than those given in the previous literature. Finally, two numerical examples and their simulations are provided to demonstrate the effectiveness of the theoretical results.     

无限时滞随机泛函微分方程的Razumikhin型定理

在无限时滞的随机泛函微分方程整体解存在的前提下,建立了一般衰减稳定性的Razumikhin型定理.在此基础上,基于局部Lipschitz条件和多项式增长条件,得到了无限时滞随机泛函微分方程整体解的存在唯一性,以及具有一般衰减速率的p阶矩和几乎必然渐近稳定性定理.     

变时滞随机Cohen-Grossberg神经网络的几乎肯定指数稳定性

通过构造Lyapunov泛函、利用半鞅收敛定理得到了变时滞随机Cohen-Grossberg神经网络几乎肯定指数稳定的判别准则.     

STABILITY IN LAGRANGE SENSE FOR A CLASS OF STOCHASTIC STATIC NEURAL NETWORKS WITH MIXED TIME DELAYS

In this paper,the stability in Lagrange sense of a class of stochastic static neural networks with mixed time delays is studied.Based on the Lyapunov stability theory and with the help of stochastic analysis technique,the criteria for the stability in Lagrange sense of stochastic static neural networks with mixed time delays is obtained.One example is given to verify the advantage and applicability of the proposed results.     

无界可变延迟神经网络的一般稳定性(英文)

本文研究了无界延迟随机神经网络的稳定性,采用的主要技巧是Razumikhin方法,得到了p阶矩一般衰减率稳定性与几乎必然轨道一般衰减率稳定性.借助于M矩阵技巧使Razumikhin定理更便于应用.     

Convergence dynamics of stochastic reaction–diffusion recurrent neural networks with continuously distributed delays

Convergence dynamics of reaction–diffusion recurrent neural networks (RNNs) with continuously distributed delays and stochastic influence are considered. Some sufficient conditions to guarantee the almost sure exponential stability, mean value exponential stability and mean square exponential stability of an equilibrium solution are obtained, respectively. Lyapunov functional method, M-matrix properties, some inequality technique and nonnegative semimartingale convergence theorem are used in our approach. These criteria ensuring the different exponential stability show that diffusion and delays are harmless, but random fluctuations are important, in the stochastic continuously distributed delayed reaction–diffusion RNNs with the structure satisfying the criteria. Two examples are also given to demonstrate our results.     

An LMI approach to stability analysis of stochastic high-order Markovian jumping neural networks with mixed time delays

This paper deals with the problem of global exponential stability for a general class of stochastic high-order neural networks with mixed time delays and Markovian jumping parameters. The mixed time delays under consideration comprise both discrete time-varying delays and distributed time-delays. The main purpose of this paper is to establish easily verifiable conditions under which the delayed high-order stochastic jumping neural network is exponentially stable in the mean square in the presence of both mixed time delays and Markovian switching. By employing a new Lyapunov–Krasovskii functional and conducting stochastic analysis, a linear matrix inequality (LMI) approach is developed to derive the criteria ensuring exponential stability. Furthermore, the criteria are dependent on both the discrete time-delay and distributed time-delay, and hence less conservative. The proposed criteria can be readily checked by using some standard numerical packages such as the Matlab LMI Toolbox. A simple example is provided to demonstrate the effectiveness and applicability of the proposed testing criteria.     

Exponential stability for stochastic reaction-diffusion BAM neural networks with time-varying and distributed delays

In this paper we study the stability for a class of stochastic bidirectional associative memory (BAM) neural networks with reaction-diffusion and mixed delays. The mixed delays considered in this paper are time-varying and distributed delays. Based on a new Lyapunov-Krasovskii functional and the Poincaré inequality as well as stochastic analysis theory, a set of novel sufficient conditions are obtained to guarantee the stochastically exponential stability of the trivial solution or zero solution. The obtained results show that the reaction-diffusion term does contribute to the exponentially stabilization of the considered system. Moreover, two numerical examples are given to show the effectiveness of the theoretical results.     

Exponential stability for stochastic BAM networks with discrete and distributed delays

In this paper, we investigate exponential stability for stochastic BAM networks with mixed delays. The mixed delays include discrete and distributed time-delays. The purpose of this paper is to establish some criteria to ensure the delayed stochastic BAM neural networks are exponential stable in the mean square. A sufficient condition is established by consructing suitable Lyapunov functionals. The condition is expressed in terms of the feasibility to a couple LMIs. Therefore, the exponential stability of the stochastic BAM networks with discrete and distributed delays can be easily checked by using the numerically efficient Matlab LMI toobox. A simple example is given to demonstrate the usefulness of the derived LMI-based stability conditions.     

Global asymptotic stability of stochastic Cohen-Grossberg-type BAM neural networks with mixed delays: An LMI approach

In this paper, we consider the stochastic Cohen-Grossberg-type BAM neural networks with mixed delays. By utilizing the Lyapunov-Krasovskii functional and the linear matrix inequality (LMI) approach, some sufficient LMI-based conditions are obtained to guarantee the global asymptotic stability of stochastic Cohen-Grossberg-type BAM neural networks with mixed delays. These conditions can be easily checked via the MATLAB LMI toolbox. Moreover, the obtained results extend and improve the earlier publications. Finally, a numerical example is provided to demonstrate the low conservatism and effectiveness of the proposed LMI conditions.     

Global exponential stability for interval general bidirectional associative memory (BAM) neural networks with proportional delays

This paper is concerned with interval general bidirectional associative memory (BAM) neural networks with proportional delays. Using appropriate nonlinear variable transformations, the interval general BAM neural networks with proportional delays can be equivalently transformed into the interval general BAM neural networks with constant delays. The sufficient condition for the existence and uniqueness of equilibrium point of the model is established by applying Brouwer's fixed point theorem. By constructing suitable delay differential inequalities, some sufficient conditions for the global exponential stability of the model are obtained. Two examples are given to illustrate the effectiveness of the obtained results. This paper ends with a brief conclusion. Copyright © 2016 John Wiley & Sons, Ltd.     

细胞神经网络的指数稳定性

该文研究了具有可变时滞的随机细胞神经网络的指数 稳定性,应用Razumikhin定理与Lyapunov函数,建立了这种细胞神经网络均方指数稳定与几乎必然指数稳定的两类判据,一类是时滞无关而另一类是时滞相关.     

LMI conditions for stability of impulsive stochastic Cohen–Grossberg neural networks with mixed delays

In this paper, the global asymptotic stability of impulsive stochastic Cohen–Grossberg neural networks with mixed delays is investigated by using Lyapunov–Krasovskii functional method and the linear matrix inequality (LMI) technique. The mixed time delays comprise both the multiple time-varying and continuously distributed delays. Some new sufficient conditions are obtained to guarantee the global asymptotic stability of the addressed model in the stochastic sense using the powerful MATLAB LMI toolbox. The results extend and improve the earlier publications. Two numerical examples are given to illustrate the effectiveness of our results.     

Existence and global exponential stability of pseudo almost periodic solution for SICNNs with mixed delays

Shunting Inhibitory Artificial Neural Networks are biologically inspired networks in which the synaptic interactions are mediated via a nonlinear mechanism called shunting inhibition, which allows neurons to operate as adaptive nonlinear filters. This paper considers the problem of existence and exponential stability of the pseudo almost periodic solution for shunting inhibitory cellular neural networks with mixed delays. The Banach fixed point theorem and the variant of a certain integral inequality with explicit estimate are used to establish the results. The results of this paper are new and they complement previously known results.     

Adaptive synchronization for stochastic competitive neural networks with mixed time-varying delays

This paper deals with the synchronization problem for competitive neural networks with different time scales, as well as mixed time-varying delays (both discrete and distributed time-varying delays) and stochastic disturbance. By using stochastic analysis approaches and constructing a novel Lyapunov–Krasovskii functional, an adaptive feedback controller is proposed to guarantee the exponential synchronization of proposed competitive neural networks in terms of p-norm. The synchronization results presented in this paper generalize and improve many known results. This paper also presents an illustrative example and uses simulated results of this example to show the feasibility and effectiveness of the theoretical results.     

Dynamic analysis of stochastic bidirectional associative memory neural networks with delays

In this paper, stochastic bidirectional associative memory neural networks model with delays is considered. By constructing Lyapunov functionals, and using stochastic analysis method and inequality technique, we give some sufficient criteria ensuring almost sure exponential stability, pth exponential stability and mean value exponential stability. The obtained criteria can be used as theoretic guidance to stabilize neural networks in practical applications when stochastic noise is taken into consideration.     

Almost periodic solution of Cohen–Grossberg neural networks with bounded and unbounded delays

In this paper, a class of Cohen–Grossberg neural networks with bounded and unbounded delays is discussed. Several new sufficient conditions are obtained ensuring the existence and exponential stability of the almost periodic solution for this model based on inequality analysis technique and combing the exponential dichotomy with fixed point theorem. The obtained results are helpful to design globally exponentially stable almost periodic oscillatory neural networks. Two numerical examples and simulations are also given to show the feasibility of our results.     

Exponential stability for stochastic jumping BAM neural networks with time-varying and distributed delays

In this paper we study the stability for a class of stochastic jumping bidirectional associative memory (BAM) neural networks with time-varying and distributed delays. To the best of our knowledge, this class of stochastic jumping BAM neural networks with time-varying and distributed delays has never been investigated in the literature. The main aim of this paper tries to fill the gap. By using the stochastic stability theory, the properties of a Brownian motion, the generalized Ito’s formula and linear matrix inequalities technique, some novel sufficient conditions are obtained to guarantee the stochastically exponential stability of the trivial solution or zero solution. In particular, the activation functions considered in this paper are fairly general since they may depend on Markovian jump parameters and they are more general than those usual Lipschitz conditions. Also, the derivative of time delays is not necessarily zero or small than 1. In summary, the results obtained in this paper extend and improve those not only with/without noise disturbances, but also with/without Markovian jump parameters. Finally, two interesting examples are provided to illustrate the theoretical results.     

混合时滞的随机微分方程的稳定性研究

本文研究了混合时滞的随机微分方程的稳定性,利用Lyapunov函数方法和半鞅收敛定理得到了p阶矩指数稳定和几乎必然指数稳定的判定定理.M矩阵技巧的使用使所得结果更便于应用.最后举例说明了结果的实用性.     

Measure Pseudo Almost Periodic Solutions of Shunting Inhibitory Cellular Neural Networks with Mixed Delays

In this work, we consider a class of neutral shunting inhibitory cellular neural networks with mixed delays. We study the existence, uniqueness, and the exponential stability of the measure pseudo almost periodic (or μ-pseudo almost periodic) solutions from some models for shunting inhibitory cellular neural networks with mixed delays. An example is provided to illustrate the theory developed in this work.