An Overview of the Stability Analysis of Recurrent Neural Networks With Multiple Equilibria

The stability analysis of recurrent neural networks (RNNs) with multiple equilibria has received extensive interest since it is a prerequisite for successful applications of RNNs. With the increasing theoretical results on this topic, it is desirable to review the results for a systematical understanding of the state of the art. This article provides an overview of the stability results of RNNs with multiple equilibria including complete stability and multistability. First, preliminaries on the complete stability and multistability analysis of RNNs are introduced. Second, the complete stability results of RNNs are summarized. Third, the multistability results of various RNNs are reviewed in detail. Finally, future directions in these interesting topics are suggested.

Limit set dichotomy and multistability for a class of cooperative neural networks with delays

Recent papers have pointed out the interest to study convergence in the presence of multiple equilibrium points (EPs) (multistability) for neural networks (NNs) with nonsymmetric cooperative (nonnegative) interconnections and neuron activations modeled by piecewise linear (PL) functions. One basic difficulty is that the semiflows generated by such NNs are monotone but, due to the horizontal segments in the PL functions, are not eventually strongly monotone (ESM). This notwithstanding, it has been shown that there are subclasses of irreducible interconnection matrices for which the semiflows, although they are not ESM, enjoy convergence properties similar to those of ESM semiflows. The results obtained so far concern the case of cooperative NNs without delays. The goal of this paper is to extend some of the existing results to the relevant case of NNs with delays. More specifically, this paper considers a class of NNs with PL neuron activations, concentrated delays, and a nonsymmetric cooperative interconnection matrix A and delay interconnection matrix A(τ). The main result is that when A+A(τ) satisfies a full interconnection condition, then the generated semiflows, which are monotone but not ESM, satisfy a limit set dichotomy analogous to that valid for ESM semiflows. It follows that there is an open and dense set of initial conditions, in the state space of continuous functions on a compact interval, for which the solutions converge toward an EP. The result holds in the general case where the NNs possess multiple EPs, i.e., is a result on multistability, and is valid for any constant value of the delays.

Exponential stability of delayed and impulsive cellular neural networks with partially Lipschitz continuous activation functions

The paper discusses exponential stability of distributed delayed and impulsive cellular neural networks with partially Lipschitz continuous activation functions. By relative nonlinear measure method, some novel criteria are obtained for the uniqueness and exponential stability of the equilibrium point. Our method abandons usual assumptions on global Lipschitz continuity, boundedness and monotonicity of activation functions. Our results are generalization and improvement of some existing ones. Finally, two examples and their simulations are presented to illustrate the correctness of our analysis.

NOVEL STABILITY CRITERIA FOR DELAYED CELLULAR NEURAL NETWORKS

In this paper, a new sufficient condition is given for the global asymptotic stability and global exponential output stability of a unique equilibrium points of delayed cellular neural networks (DCNNs) by using Lyapunov method. This condition imposes constraints on the feedback matrices and delayed feedback matrices of DCNNs and is independent of the delay. The obtained results extend and improve upon those in the earlier literature, and this condition is also less restrictive than those given in the earlier references. Two examples compared with the previous results in the literatures are presented and a simulation result is also given.

ANALYSIS OF A CLASS OF RECURRENT NEURAL NETWORKS WITH ARBITRARY EXPONENTS

This paper deals with problems of stability and travelling waves for a class of recurrent neural networks with arbitrary exponents k and m. A novel model which is not only nonlinear but also coupled is proposed. This paper makes the following contributions: (1) Conditions for local stablility of 1-D networks and 2-D networks are established with a series of mathematical arguments. (2) Completely convergence of 1-D neural networks is proved by constructing a suitable energy function. (3) The nonuniform solution of the networks is obtained when the connectivity is Gaussian profile. (4) Travelling waves of the networks are analyzed with the connectivity profile. Finally, simulation examples are employed to illustrate the obtained results.

Analysis of complete stability for discrete-time cellular neural networks with piecewise linear output functions

This letter discusses the complete stability of discrete-time cellular neural networks with piecewise linear output functions. Under the assumption of certain symmetry on the feedback matrix, a sufficient condition of complete stability is derived by finite trajectory length. Because the symmetric conditions are not robust, the complete stability of networks may be lost under sufficiently small perturbations. The robust conditions of complete stability are also given for discrete-time cellular neural networks with multiple equilibrium points and a unique equilibrium point. These complete stability results are robust and available.

Complete Stability in Multistable Delayed Neural Networks

We investigate the complete stability for multistable delayed neural networks. A new formulation modified from the previous studies on multistable networks is developed to derive componentwise dynamical property. An iteration argument is then constructed to conclude that every solution of the network converges to a single equilibrium as time tends to infinity. The existence of 3n equilibria and 2n positively invariant sets for the n-neuron system remains valid under the new formulation. The theory is demonstrated by a numerical illustration.

Asymptotic stability criteria for a two-neuron network with different time delays

In this paper, the asymptotic stability of a two-neuron system with different time delays has been investigated. Some criteria for determining the global asymptotically stability of equilibrium are derived from the theory of monotonic dynamical system and the approach of Lyapunov functional. For local asymptotic stability, some elegant criteria are also obtained by the Nyquist criteria. We find that one of them depends on the length of delays while the other ones do not. In the latter case, the delays are sometimes called harmless delays. The results obtained have leading significance in the study of neural networks composed of a large number of neurons with different time delays.

Global point dissipativity of neural networks with mixed time-varying delays

By employing the Lyapunov method and some inequality techniques, the global point dissipativity is studied for neural networks with both discrete time-varying delays and distributed time-varying delays. Simple sufficient conditions are given for checking the global point dissipativity of neural networks with mixed time-varying delays. The proposed linear matrix inequality approach is computationally efficient as it can be solved numerically using standard commercial software. Illustrated examples are given to show the usefulness of the results in comparison with some existing results.

Deriving Sufficient Conditions for Global Asymptotic Stability of Delayed Neural Networks via Nonsmooth Analysis—II

Following our recent approach of nonsmooth analysis, we report a new set of sufficient conditions and its implications for the global asymptotic stability of delayed cellular neural networks (DCNN). The new conditions not only unify a string of previous stability results, but also yield strict improvement over them by allowing the symmetric part of the feedback matrix positive definite, hence enlarging the application domain of DCNNs. Advantages of the new results over existing ones are illustrated with examples. We also compare our results with those related results obtained via LMI approach.

Global robust stability for shunting inhibitory CNNs with delays

In this paper, the problem of global robust stability for shunting inhibitory cellular neural networks (SICNNs) is studied. A sufficient condition guaranteeing the network's global robust stability is established. The result can easily be used to verify globally robust stable networks. An example is given to illustrate that the conditions of our results are feasible.

On stability of cellular neural networks with polynomial interactions

Cellular neural/nonlinear networks (CNNs) are analog dynamic processor arrays, that present local interconnections. CNN models with polynomial interactions among the cells (Polynomial type CNNs) have been recently introduced. They are useful for solving some complex computational problems and for real-time implementation of PDE-based algorithms. This manuscript provides some simple and rigorous sufficient conditions for stability of polynomial type CNNs. A particular emphasis is given to conditions that can be expressed in terms of template elements, since they can be exploited for design purposes.

Deriving Sufficient Conditions for Global Asymptotic Stability of Delayed Neural Networks via Nonsmooth Analysis

In this paper, we obtain new sufficient conditions ensuring existence, uniqueness, and global asymptotic stability (GAS) of the equilibrium point for a general class of delayed neural networks (DNNs) via nonsmooth analysis, which makes full use of the Lipschitz property of functions defining DNNs. Based on this new tool of nonsmooth analysis, we first obtain a couple of general results concerning the existence and uniqueness of the equilibrium point. Then those results are applied to show that existence assumptions on the equilibrium point in some existing sufficient conditions ensuring GAS are actually unnecessary; and some strong assumptions such as the boundedness of activation functions in some other existing sufficient conditions can be actually dropped. Finally, we derive some new sufficient conditions which are easy to check. Comparison with some related existing results is conducted and advantages are illustrated with examples. Throughout our paper, spectral properties of the matrix (A + Atau) play an important role, which is a distinguished feature from previous studies. Here, A and Atau are, respectively, the feedback and the delayed feedback matrix defining the neural network under consideration.

Dynamic stability conditions for Lotka-Volterra recurrent neural networks with delays

The Lotka-Volterra model of neural networks, derived from the membrane dynamics of competing neurons, have found successful applications in many "winner-take-all" types of problems. This paper studies the dynamic stability properties of general Lotka-Volterra recurrent neural networks with delays. Conditions for nondivergence of the neural networks are derived. These conditions are based on local inhibition of networks, thereby allowing these networks to possess a multistability property. Multistability is a necessary property of a network that will enable important neural computations such as those governing the decision making process. Under these nondivergence conditions, a compact set that globally attracts all the trajectories of a network can be computed explicitly. If the connection weight matrix of a network is symmetric in some sense, and the delays of the network are in L2 space, we can prove that the network will have the property of complete stability.

On stability of nonlinear continuous-time neural networks with delays

We utilize the Lyapunov function method to analyze stability of continuous nonlinear neural networks with delays and obtain some new sufficient conditions ensuring the globally asymptotic stability independent of delays. Three main conditions imposed on the weighting matrices are established. (i). The spectral radius rho(M(-1)(W0 + Wtau)K) < 1. (ii). The row norm M(-1)(W0 + Wtau)K + P(-1) ((W0 + Wtau)KM(-1))T P infinity < 2. (iii). mu2(W0) + Wtau2,F < (m/k). These three conditions are independent to each other. The delayed Hopfield network, Bidirectional associative memory network and cellular neural network are special cases of the network model considered in this paper. So we improve some previous works of other researchers.

Periodic solutions and exponential stability in delayed cellular neural networks

Some simple sufficient conditions are given ensuring global exponential stability and the existence of periodic solutions of delayed cellular neural networks (DCNNs) by constructing suitable Lyapunov functionals and some analysis techniques. These conditions are easy to check in terms of system parameters and have important leading significance in the design and applications of globally stable DCNNs and periodic oscillatory DCNNs. In addition, two examples are given to illustrate the theory.

On the analysis of neural networks with asymmetric connection weights or noninvertible transfer functions

This paper extends the energy function to the analysis of the stability of neural networks with asymmetric interconnections and noninvertible transfer functions. Based on the new energy function, stability theorems and convergent criteria are derived which improve the available results in the literature. A simpler proof of a previous result for complete stability is given. Theorems on complete stability of neural networks with noninvertible output functions are presented.