Multistability of Recurrent Neural Networks With Time-varying Delays and the Piecewise Linear Activation Function

Exponential stability of memristor-based synchronous switching neural networks with time delays

In this paper, we study the existence, uniqueness and stability of memristor-based synchronous switching neural networks with time delays. Several criteria of exponential stability are given by introducing multiple Lyapunov functions. In comparison with the existing publications on simplice memristive neural networks or switching neural networks, we consider a system with a series of switchings, these switchings are assumed to be synchronous with memristive switching mechanism. Moreover, the proposed stability conditions are straightforward and convenient and can reflect the impact of time delay on the stability. Two examples are also presented to illustrate the effectiveness of the theoretical results.

Multistability and Instability of Neural Networks With Discontinuous Nonmonotonic Piecewise Linear Activation Functions

In this paper, we discuss the coexistence and dynamical behaviors of multiple equilibrium points for recurrent neural networks with a class of discontinuous nonmonotonic piecewise linear activation functions. It is proved that under some conditions, such n -neuron neural networks can have at least 5(n) equilibrium points, 3(n) of which are locally stable and the others are unstable, based on the contraction mapping theorem and the theory of strict diagonal dominance matrix. The investigation shows that the neural networks with the discontinuous activation functions introduced in this paper can have both more total equilibrium points and more locally stable equilibrium points than the ones with continuous Mexican-hat-type activation function or discontinuous two-level activation functions. An illustrative example with computer simulations is presented to verify the theoretical analysis.

Passivity and Synchronization of Linearly Coupled Reaction-Diffusion Neural Networks With Adaptive Coupling

In this paper, we study a general array model of coupled reaction-diffusion neural networks (NNs) with adaptive coupling. In order to ensure the passivity of the coupled reaction-diffusion neural networks, some adaptive strategies to tune the coupling strengths among network nodes are designed. By utilizing some inequality techniques and the designed adaptive laws, several sufficient conditions ensuring passivity are obtained. In addition, we reveal the relationship between passivity and synchronization of the coupled reaction-diffusion NNs. Based on the obtained passivity results and the relationship between passivity and synchronization, a global synchronization criterion is established. Finally, numerical simulations are presented to illustrate the correctness and effectiveness of the proposed results.

Multistability in a class of stochastic delayed Hopfield neural networks

In this paper, multistability analysis for a class of stochastic delayed Hopfield neural networks is investigated. By considering the geometrical configuration of activation functions, the state space is divided into 2(n) + 1 regions in which 2(n) regions are unbounded rectangles. By applying Schauder's fixed-point theorem and some novel stochastic analysis techniques, it is shown that under some conditions, the 2(n) rectangular regions are positively invariant with probability one, and each of them possesses a unique equilibrium. Then by applying Lyapunov function and functional approach, two multistability criteria are established for ensuring these equilibria to be locally exponentially stable in mean square. The first multistability criterion is suitable to the case where the information on delay derivative is unknown, while the second criterion requires that the delay derivative be strictly less than one. For the constant delay case, the second multistability criterion is less conservative than the first one. Finally, an illustrative example is presented to show the effectiveness of the derived results.

Robust stability of stochastic fuzzy delayed neural networks with impulsive time window

The urgent problem of impulsive moments which cannot be determined in advance brings new challenges beyond the conventional impulsive systems theory. In order to solve this problem, the novel concept of impulsive time window is proposed in this paper. And the stability problem of stochastic fuzzy uncertain delayed neural networks with impulsive time window is investigated. By combining the discretized Lyapunov function approach with mathematical induction method, several novel and easy-to-check sufficient conditions concerning the impulsive time window are derived to ensure that the model considered here is exponentially stable in mean square. Numerical simulations are presented to further demonstrate the effectiveness of the proposed stability criterion.

Attractivity analysis of memristor-based cellular neural networks with time-varying delays

This paper presents new theoretical results on the invariance and attractivity of memristor-based cellular neural networks (MCNNs) with time-varying delays. First, sufficient conditions to assure the boundedness and global attractivity of the networks are derived. Using state-space decomposition and some analytic techniques, it is shown that the number of equilibria located in the saturation regions of the piecewise-linear activation functions of an n-neuron MCNN with time-varying delays increases significantly from 2(n) to 2(2n2)+n) (2(2n2) times) compared with that without a memristor. In addition, sufficient conditions for the invariance and local or global attractivity of equilibria or attractive sets in any designated region are derived. Finally, two illustrative examples are given to elaborate the characteristics of the results in detail.

Multistability of two kinds of recurrent neural networks with activation functions symmetrical about the origin on the phase plane

In this paper, we investigate multistability of two kinds of recurrent neural networks with time-varying delays and activation functions symmetrical about the origin on the phase plane. One kind of activation function is with zero slope at the origin on the phase plane, while the other is with nonzero slope at the origin on the phase plane. We derive sufficient conditions under which these two kinds of n-dimensional recurrent neural networks are guaranteed to have (2m+1)(n) equilibrium points, with (m+1)(n) of them being locally exponentially stable. These new conditions improve and extend the existing multistability results for recurrent neural networks. Finally, the validity and performance of the theoretical results are demonstrated through two numerical examples.

Exponential stabilization of memristive neural networks with time delays

In this paper, a general class of memristive neural networks with time delays is formulated and studied. Some sufficient conditions in terms of linear matrix inequalities are obtained, in order to achieve exponential stabilization. The result can be applied to the closed-loop control of memristive systems. In particular, several succinct criteria are given to ascertain the exponential stabilization of memristive cellular neural networks. In addition, a simplified and effective algorithm is considered for design of the optimal controller. These conditions are the improvement and extension of the existing results in the literature. Two numerical examples are given to illustrate the theoretical results via computer simulations.

Multistability of neural networks with Mexican-hat-type activation functions

In this paper, we are concerned with a class of neural networks with Mexican-hat-type activation functions. Due to the different structure from neural networks with saturated activation functions, a set of new sufficient conditions are presented to study the multistability, including the total number of equilibrium points, their locations, and stability. Furthermore, the attraction basins of stable equilibrium points are investigated for two-neuron neural networks. The investigation shows that the stable manifolds of unstable equilibrium points constitute the boundaries of attraction basins of stable equilibrium points. Several illustrative examples are given to verify the effectiveness of our results.

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.

Solving the assignment problem using continuous-time and discrete-time improved dual networks

The assignment problem is an archetypal combinatorial optimization problem. In this brief, we present a continuous-time version and a discrete-time version of the improved dual neural network (IDNN) for solving the assignment problem. Compared with most assignment networks in the literature, the two versions of IDNNs are advantageous in circuit implementation due to their simple structures. Both of them are theoretically guaranteed to be globally convergent to a solution of the assignment problem if only the solution is unique.

Multistability of neural networks with time-varying delays and concave-convex characteristics

In this paper, stability of multiple equilibria of neural networks with time-varying delays and concave-convex characteristics is formulated and studied. Some sufficient conditions are obtained to ensure that an n-neuron neural network with concave-convex characteristics can have a fixed point located in the appointed region. By means of an appropriate partition of the n-dimensional state space, when nonlinear activation functions of an n-neuron neural network are concave or convex in 2k+2m-1 intervals, this neural network can have (2k+2m-1)n equilibrium points. This result can be applied to the multiobjective optimal control and associative memory. In particular, several succinct criteria are given to ascertain multistability of cellular neural networks. These stability conditions are the improvement and extension of the existing stability results in the literature. A numerical example is given to illustrate the theoretical findings via computer simulations.

Robustness analysis of global exponential stability of recurrent neural networks in the presence of time delays and random disturbances

In recent years, the global stability of recurrent neural networks (RNNs) has been investigated extensively. It is well known that time delays and external disturbances can derail the stability of RNNs. In this paper, we analyze the robustness of global stability of RNNs subject to time delays and random disturbances. Given a globally exponentially stable neural network, the problem to be addressed here is how much time delay and noise the RNN can withstand to be globally exponentially stable in the presence of delay and noise. The upper bounds of the time delay and noise intensity are characterized by using transcendental equations for the RNNs to sustain global exponential stability. Moreover, we prove theoretically that, for any globally exponentially stable RNNs, if additive noises and time delays are smaller than the derived lower bounds arrived at here, then the perturbed RNNs are guaranteed to also be globally exponentially stable. Three numerical examples are provided to substantiate the theoretical results.