Stability Analysis of Gradient-Based Neural Networks for Optimization Problems

The paper introduces a new approach to analyze the stability of neural network models without using any Lyapunov function. With the new approach, we investigate the stability properties of the general gradient-based neural network model for optimization problems. Our discussion includes both isolated equilibrium points and connected equilibrium sets which could be unbounded. For a general optimization problem, if the objective function is bounded below and its gradient is Lipschitz continuous, we prove that (a) any trajectory of the gradient-based neural network converges to an equilibrium point, and (b) the Lyapunov stability is equivalent to the asymptotical stability in the gradient-based neural networks. For a convex optimization problem, under the same assumptions, we show that any trajectory of gradient-based neural networks will converge to an asymptotically stable equilibrium point of the neural networks. For a general nonlinear objective function, we propose a refined gradient-based neural network, whose trajectory with any arbitrary initial point will converge to an equilibrium point, which satisfies the second order necessary optimality conditions for optimization problems. Promising simulation results of a refined gradient-based neural network on some problems are also reported.     

带马尔可夫跳的随机Hopfield神经网络的以分布渐近稳定性

讨论了带马尔可夫跳的随机Hopfield神经网络的以分布渐近稳定性.通过构造合适的Lyapunov函数,获得了判定带马尔可夫跳的随机Hopfield神经网络的以分布渐近稳定性的充分条件.     

Stability analysis for neural networks with inverse Lipschitzian neuron activations and impulses

In this paper, a new concept called α-inverse Lipschitz function is introduced. Based on the topological degree theory and Lyapunov functional method, we investigate global convergence for a novel class of neural networks with impulses where the neuron activations belong to the class of α-inverse Lipschitz functions. Some sufficient conditions are derived which ensure the existence, and global exponential stability of the equilibrium point of neural networks. Furthermore, we give two results which are used to check the stability of uncertain neural networks. Finally, two numerical examples are given to demonstrate the effectiveness of results obtained in this paper.     

Neural networks for solving second-order cone constrained variational inequality problem

In this paper, we consider using the neural networks to efficiently solve the second-order cone constrained variational inequality (SOCCVI) problem. More specifically, two kinds of neural networks are proposed to deal with the Karush-Kuhn-Tucker (KKT) conditions of the SOCCVI problem. The first neural network uses the Fischer-Burmeister (FB) function to achieve an unconstrained minimization which is a merit function of the Karush-Kuhn-Tucker equation. We show that the merit function is a Lyapunov function and this neural network is asymptotically stable. The second neural network is introduced for solving a projection formulation whose solutions coincide with the KKT triples of SOCCVI problem. Its Lyapunov stability and global convergence are proved under some conditions. Simulations are provided to show effectiveness of the proposed neural networks.     

一类扩张的细胞神经网络稳定性判别法

本文研究一类含有阻尼项带有时滞细胞神经网络的全局渐进稳定性和一致稳定性的性质,通过构造适当的李雅普诺夫函数及利用分析的有关知识,给出了全局渐进稳定性和一致稳定的判别法．     

Global exponential stability of a class of neural networks with unbounded delays

In this paper, the global exponential stability of a class of neural networks is investigated. The neural networks contain variable and unbounded delays. By constructing a suitable Lyapunov function and using the technique of matrix analysis, we obtain some new sufficient conditions for global exponential stability. Published in Ukrains’kyi Matematychnyi Zhurnal, Vol. 60, No. 10, pp. 1401–1413, October, 2008.     

时滞Hopfield神经网络模型渐进稳定性的新准则

在不考虑激励函数有界,可微和单调的情况下,利用Lyapunov泛函方法,得到了时滞Hopfield神经网络模型的平衡点存在性和全局渐近稳定性的新准则.研究结果改进和推广了以前相关文献的结果.     

Cohen-Grossberg神经网络的全局指数稳定性分析

本文研究了CohenGrossberg神经网络模型的指数稳定性.为避免构造Lyapunov函数的困难,我们采用广义相对Dalquist数方法来分析神经网络的稳定性.借助这一方法,我们不但得到了CohenGrossberg神经网络模型平衡解的存在性、唯一性和全局指数稳定性的新的充分条件,而且给出了神经网络的指数衰减估计.所获结论改进了已有文献的相关结果.     

Exponential stability of discrete-time neural networks with delay and impulses

In this paper, we investigate the exponential stability of discrete-time neural networks with impulses and time-varying delay. The discrete-time neural networks are derived by discretizing the corresponding continuous-time counterparts with different discretization methods. The impulses are classified into three classes: input disturbances, stabilizing and “neutral” type - the impulses are neither helpful for stabilizing nor destabilizing the neural networks, and then by using the excellent ideology introduced recently by Chen and Zheng [W.H. Chen, W.X. Zheng, Global exponential stability of impulsive neural networks with variable delay: an LMI approach, IEEE Trans. Circuits Syst. I 56 (6) (2009) 1248-1259], the connections between the impulses and the utilized Lyapunov function are fully explored with respect to each type of impulse. Novel techniques that used to realize the ideology in discrete-time situation are proposed and it is shown that they are essentially different from the continuous-time case. Several criteria for global exponential stability of the discrete-time neural networks are established in terms of matrix inequalities and based on these theoretical results numerical simulations are given to compare the capability of different discretization methods.     

EXISTENCE AND STABILITY OF PERIODIC SOLUTIONS OF DELAYED BAM NEURAL NETWORKS WITH PERIODIC COEFFICIENTS

In this paper, we study the BAM neural networks with variable coefficients and delays. By using the Banach fixed point theorem and constructing suitable Lyapunov function, we obtain some sufficient conditions ensuring the existence, uniqueness and global stability of periodic solution. These results are helpful to design global exponential stable BAM networks and periodic oscillatory BAM networks.     

Global exponential stability of static neural networks with delay and impulses: Discrete-time case

In this paper, we investigate the exponential stability of discrete-time static neural networks with impulses and variable time delay. The discrete-time neural networks are derived by discretizing the corresponding continuous-time counterparts with implicit-explicit-θ (IMEX-θ) method. The impulses are classified into three classes: input disturbances, stabilizing and “neutral” type— the impulses are neither helpful for stabilizing nor destabilizing the neural networks, and then by using a very excellent ideology introduced recently the connections between the impulses and the utilized Lyapunov function are fully explored with respect to each type of impulse. New analysis techniques that used to realize the ideology in discrete-time situation are proposed and it is shown that they are essentially different from the ones used in continuous-time case. Several criteria for global exponential stability of the static neural networks in discrete-time case are established in terms of linear matrix inequalities (LMIs) and numerical simulations are given to validate the obtained theoretical results.     

离散分数阶神经网络的全局Mittag-Leffler稳定性

研究了一类离散分数阶神经网络的Mittag-Leffler稳定性问题.首先, 基于离散分数阶微积分理论、神经网络理论,提出了一类离散分数阶神经网络.其次,利用不等式技巧和离散Laplace变换,通过构造合适的Lyapunov函数,得到了离散分数阶神经网络全局Mittag-Leffler稳定的充分性判据.最后,通过一个数值仿真算例验证了所提出理论的有效性.     

Stability analysis for periodic solution of BAM neural networks with discontinuous neuron activations and impulses

In this paper, we present a general class of BAM neural networks with discontinuous neuron activations and impulses. By using the fixed point theorem in differential inclusions theory, we investigate the existence of periodic solution for this neural network. By constructing the suitable Lyapunov function, we give a sufficient condition which ensures the uniqueness and global exponential stability of the periodic solution. The results of this paper show that the Forti’s conjecture is true for BAM neural networks with discontinuous neuron activations and impulses. Further, a numerical example is given to demonstrate the effectiveness of the results obtained in this paper.     

Exponential stability analysis of stochastic delayed cellular neural network

In this paper, the stability of stochastic delayed cellular neural networks are studied. Via the Lyapunov function method and some analysis techniques, we obtain some new criteria of exponential 1-stability and mean square exponential stability.     

具有跳跃的随机神经网络的均方稳定性

研究了一类新的具有脉冲跳跃的Hopfield神经网络系统模型,其中脉冲时刻的跳跃是由一般的随机序列所引起,通过运用Lyapunov函数方法,获取了一些新的均方稳定性结果.由于脉冲的跳跃使得不稳定的神经网络变成稳定,因而所得的结果也可以运用到其他相关领域.     

New stability conditions for neural networks with constant and variable delays

In this paper, by utilizing Lyapunov functional method, we analyze global asymptotic stability of neural networks with constant delays. A new sufficient condition ensuring global asymptotic stability of the unique equilibrium point of delayed neural networks is obtained. Furthermore, based on the method of delay differential inequality, the conditions checking global exponential stability of the equilibrium point of neural networks with variable delays are given. The results extend and improve the earlier publications.     

A graph-theoretic approach to exponential stability of BAM neural networks with delays and reaction-diffusion

This paper deals with the problem of global exponential stability for bidirectional associate memory (BAM) neural networks with time-varying delays and reaction-diffusion terms. By using some inequality techniques, graph theory as well as Lyapunov stability theory, a systematic method of constructing a global Lyapunov function for BAM neural networks with time-varying delays and reaction-diffusion terms is provided. Furthermore, two different kinds of sufficient principles are derived to guarantee the exponential stability of BAM neural networks. Finally, a numerical example is carried out to demonstrate the effectiveness and applicability of the theoretical results.     

变时滞细胞神经网络的指数稳定的一个充分条件

本文我们研究了变时滞细胞神经网络的指数稳定性。利用分析技巧，获得了变时滞细胞神经网络的指数稳定的充分条件，改进了已有文献中的相应结果。     

New stability conditions for neural networks with constant and variable delays

In this paper, by utilizing Lyapunov functional method, we analyze global asymptotic stability of neural networks with constant delays. A new sufficient condition ensuring global asymptotic stability of the unique equilibrium point of delayed neural networks is obtained. Furthermore, based on the method of delay differential inequality, the conditions checking global exponential stability of the equilibrium point of neural networks with variable delays are given. The results extend and improve the earlier publications.