Dynamical behavior of delayed Hopfield neural networks with discontinuous activations

In this paper, a general class of neural networks with arbitrary constant delays is studied, whose neuron activations are discontinuous and may be unbounded or nonmonotonic. Based on the Leray–Schauder alternative principle and generalized Lyapunov approach, conditions are given under which there is a unique equilibrium of the neural network, which is globally asymptotically stable. Moreover, the existence and global asymptotic stability of periodic solutions are derived, where the neuron inputs are periodic. The obtained results extend previous works not only on delayed neural networks with Lipschitz continuous neuron activations, but also on delayed neural networks with discontinuous neuron activations.     

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.     

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

In this paper, we present a general class of neural networks with discontinuous neuron activations and varying coefficients, where the neuron activation function is a discontinuous monotone increasing and bounded function. By using the fixed point theorem in differential inclusion theory and constructing suitable Lyapunov functions, a condition is derived which ensures the existence and global exponential stability of a unique periodic solution for the neural network. Furthermore, under certain conditions global convergence in finite time of the state is investigated. The obtained results show that Forti’s conjecture for neural networks without delays is true. Finally, two numerical examples are given to demonstrate the effectiveness of the results obtained in this paper.     

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.     

Almost periodicity for a class of delayed Cohen–Grossberg neural networks with discontinuous activations

The objective of this paper is to investigate the dynamics of a class of delayed Cohen–Grossberg neural networks with discontinuous neuron activations. By means of retarded differential inclusions, we obtain a result on the local existence of solutions, which improves the previous related results for delayed neural networks. It is shown that an M-matrix condition satisfied by the neuron interconnections, can guarantee not only the existence and uniqueness of an almost periodic solution, but also its global exponential stability. It is also shown that the M-matrix condition ensures that all solutions of the system display a common asymptotic behavior. In this paper, we prove that the existence interval of the almost periodic solution is (?∞, +∞), whereas the existence interval is only proved to be [0, +∞) in most of the literature. As special cases, we derive the results of existence, uniqueness and global exponential stability of a periodic solution for delayed neural networks with periodic coefficients, as well as the similar results of an equilibrium for the systems with constant coefficients. To the author’s knowledge, the results in this paper are the only available results on almost periodicity for Cohen–Grossberg neural networks with discontinuous activations and delays.     

Finite-time synchronization of master-slave neural networks with time-delays and discontinuous activations

This paper deals with the finite-time synchronization issue of time-varying delayed neural networks (DNNs) with discontinuous activations. Based on master-slave concept, several sufficient conditions are given to guarantee the finite-time synchronization of discontinuous DNNs. In order to control the synchronization error to converge zero in a finite time, we design three classes of novel switching state-feedback controllers which involve time-delays and discontinuous factors. The analysis in this paper employs the extended differential inclusion theory, the famous finite-time stability theorem, inequality techniques and generalized Lyapunov approach. Moreover, the upper bounds of the settling time of synchronization are estimated. Finally, the validity of proposed design method and theoretical results are illustrated by numerical examples.     

A new sufficient condition for global robust stability of bidirectional associative memory neural networks with multiple time delays

This paper presents an easily verifiable delay independent sufficient condition for the global robust asymptotic stability of the equilibrium point for bidirectional associative memory (BAM) neural networks with time delays by employing a class of Lyapunov functionals. The obtained results are applicable to all bounded continuous non-monotonic neuron activation functions. Some numerical examples are given to compare our results with the previous robust stability results derived in the literature.     

SYNCHRONIZATION OF TWO COUPLED HINDMARSH-ROSE NEURONS BY A PACEMAKER

This paper considers the synchronization of two coupled Hindmarsh-Rose neurons by a pacemaker.Based on the stability theory of differential equations,the complete synchronization of this pacemaker neuron model is reached.Moreover,we also show that pacemaker can enhance or induce synchronization.Numerical simulations are given to illustrate the main results.     

Exponential synchronization of discontinuous chaotic systems via delayed impulsive control and its application to secure communication

This paper investigates drive-response synchronization of chaotic systems with discontinuous right-hand side. Firstly, a general model is proposed to describe most of known discontinuous chaotic system with or without time-varying delay. An uniform impulsive controller with multiple unknown time-varying delays is designed such that the response system can be globally exponentially synchronized with the drive system. By utilizing a new lemma on impulsive differential inequality and the Lyapunov functional method, several synchronization criteria are obtained through rigorous mathematical proofs. Results of this paper are universal and can be applied to continuous chaotic systems. Moreover, numerical examples including discontinuous chaotic Chen system, memristor-based Chua’s circuit, and neural networks with discontinuous activations are given to verify the effectiveness of the theoretical results. Application of the obtained results to secure communication is also demonstrated in this paper.     

The LMI method for stationary oscillation of interval neural networks with three neuron activations under impulsive effects

In this paper, we investigate the stationary oscillation of interval neural networks with three neuron activation functions and time-varying delays under impulsive perturbations. Several theorems are given which present some sufficient conditions to guarantee the existence, uniqueness, and global exponential stability of periodic solutions (i.e., stationary oscillation) based on Lyapunov functionals approach and inequality analysis techniques. The obtained results can be easily checked by the Linear Matrix Inequality control toolbox in MATLAB. Finally, an example is given to illustrate the advantage of the obtained results.     

THE STABILITY IN NEURAL NETWORK WITH DELAY AND DYNAMICAL THRESHOLDEFFECTS

1 IntroductionThe researches on dynamics of neural network systems have been arousinga great deal of interests for more than thirty years. In last ten years, many.researches focused on the study of dynamics of neural network models withdelay. In fact, neural networks often have times delay in reality, for exampledue to the finite switching speed of amplifiers in electronic neural networks.Thus, a large amount of excellent results appeared consecutively [1]--[5]. In thispaper, what we study is…     

Limits of applicability of a spherical model for solving problems of electroencephalography

Methods are developed for the localization of neuron brain sources with the potential recorded as an electroencephalogram (EEG). A boundary-value problem for a Poisson equation is considered. A boundary Fredholm integral equation of the second kind is deduced. A method for numerically solving an integral equation is proposed, and the results from a number of computing experiments are given.     

Synchronization of fractional‐order chaotic systems with disturbances via novel fractional‐integer integral sliding mode control and application to neuron models

In this paper, a novel fractional‐integer integral type sliding mode technique for control and generalized function projective synchronization of different fractional‐order chaotic systems with different dimensions in the presence of disturbances is presented. When the upper bounds of the disturbances are known, a sliding mode control rule is proposed to insure the existence of the sliding motion in finite time. Furthermore, an adaptive sliding mode control is designed when the upper bounds of the disturbances are unknown. The stability analysis of sliding mode surface is given using the Lyapunov stability theory. Finally, the results performed for synchronization of three‐dimensional fractional‐order chaotic Hindmarsh‐Rose (HR) neuron model and two‐dimensional fractional‐order chaotic FitzHugh‐Nagumo (FHN) neuron model.     

Bifurcation analysis on a discrete-time tabu learning model

In this paper, we consider a discrete-time tabu learning single neuron model. After investigating the stability of the given system, we demonstrate that Pichfork bifurcation, Flip bifurcation and Neimark–Sacker bifurcation will occur when the bifurcation parameter exceed a critical value, respectively. A formula is given for determining the direction and stability of Neimark–Sacker bifurcation by applying the normal form theory and the center manifold theorem. Some numerical simulations for justifying the theoretical results are also provided.     

不连续激活函数的时滞神经网络的多稳定性

研究了不连续激活函数的时滞神经网络的多稳定性问题,在所研究的神经网络中,激活函数并不需要是连续的和单调的．给出了判断该神经网络多个平衡点存在及局部指数稳定的充分条件．最后,给出了两个数值仿真例子来验证本文获得结果的有效性和较小的保守性．     

Numerical Analysis of Boundary-Value Problems for Singularly-Perturbed Differential-Difference Equations with Small Shifts of Mixed Type

In this paper, we use a numerical method to solve boundary-value problems for a singularly-perturbed differential-difference equation of mixed type, i.e., containing both terms having a negative shift and terms having a positive shift. Similar boundary-value problems are associated with expected first exit time problems of the membrane potential in models for the neuron. The stability and convergence analysis of the method is given. The effect of a small shift on the boundary-layer solution is shown via numerical experiments. The numerical results for several test examples demonstrate the efficiency of the method.     

Global dissipativity of mixed time-varying delayed neural networks with discontinuous activations

In this paper, the problems of global dissipativity are investigated for neural networks with mixed time-varying delays and discontinuous activations. Some new criteria for checking the global dissipativity of the addressed neural networks are established by constructing appropriate Lyapunov functionals and employing the theory of Filippov systems and M-matrix properties. Finally, two numerical examples with simulations are presented to demonstrate the effectiveness of the theoretical results.     

New results on exponential passivity of neural networks with time-varying delays

The problem of delay-dependent exponential passivity analysis is investigated for neural networks with time-varying delays. By use of a linear matrix inequality (LMI) approach, a new exponential passivity criterion is proposed via the full use of the information of neuron activation functions and the involved time-varying delays. The obtained results have less conservativeness and less number of decision variables than the existing ones. A numerical example is given to demonstrate the effectiveness and the reduced conservatism of the derived results.     

FPGA Realization of Fractional Order Neuron

In this paper fractional Hindmarsh Rose (HR) neuron, which mimics several behaviors of a real biological neuron is implemented on field programmable gate array (FPGA). The results show several differences in the dynamic characteristics of integer and fractional order Hindmarsh Rose neuron models. The integer order model shows only one type of firing characteristics when the parameters of model remains same. The fractional order model depicts several dynamical behaviors even for the same parameters as the order of the fractional operator is varied. The firing frequency increases when the order of the fractional operator decreases. The fractional order is therefore key in determining the firing characteristics of biological neurons. To implement this neuron model first the digital realization of different fractional operator approximations are obtained, then the fractional integrator is used to obtain the low power and low cost hardware realization of fractional HR neuron. The fractional neuron model has been implemented on a low voltage and low power circuit and then compared with its integer counter part. The hardware is used to demonstrate the different dynamical behaviors of fractional HR neuron for different type of approximations obtained for fractional operator in this paper. A coupled network of fractional order HR neurons is also implemented. The results also show that synchronization between neurons increases as long as coupling factor keeps on increasing.     

Impulsive synchronization seeking in general complex delayed dynamical networks

The present paper investigates the issues of impulsive synchronization seeking in general complex delayed dynamical networks with nonsymmetrical coupling. By establishing the extended Halanay differential inequality on impulsive delayed dynamical systems, some simple yet generic sufficient conditions for global exponential synchronization of the impulsive controlled delayed dynamical networks are derived analytically. Compared with some existing works, the distinctive features of these sufficient conditions indicate two aspects: on the one hand, these sufficient conditions can provide an effective impulsive control scheme to synchronize an arbitrary given delayed dynamical network to a desired synchronization state even if the original given network may be asynchronous itself. On the other hand, the controlled synchronization state can be selected as a weighted average of all the states in the network for the purpose of practical control strategy, which reveals the contributions and influences of various nodes in synchronization seeking processes of the dynamical networks. It is shown that impulses play an important role in making the delayed dynamical networks globally exponentially synchronized. Furthermore, the results are applied to a typical nearest-neighbor unidirectional time-delay coupled networks composed of chaotic FHN neuron oscillators, and numerical simulations are given to demonstrate the effectiveness of the proposed control methodology.