Global exponential stability of non-autonomous FCNNs with Dirichlet boundary conditions and reaction–diffusion terms

In this paper, we investigate the global exponential stability of non-autonomous fuzzy cellular neural networks (FCNNs) with Dirichlet boundary conditions and reaction–diffusion terms. By constructing a suitable Lyapunov functional and utilizing some inequality techniques, we obtain some sufficient conditions for the uniqueness and global exponential stability of the equilibrium solution. The result is easy to check and plays an important role in the design and applications of globally exponentially stable fuzzy neural circuits. Finally, the utility of our result is illustrated via a numerical example.     

Stability analysis of impulsive Cohen–Grossberg neural networks with distributed delays and reaction–diffusion terms

In this paper, we investigate a class of impulsive Cohen–Grossberg neural networks with distributed delays and reaction–diffusion terms. By establishing an integro-differential inequality with impulsive initial conditions and applying M-matrix theory, we find some sufficient conditions ensuring the existence, uniqueness, global exponential stability and global robust exponential stability of equilibrium point for impulsive Cohen–Grossberg neural networks with distributed delays and reaction–diffusion terms. An example is given to illustrate the results obtained here.     

Global exponential stability of fuzzy cellular neural networks with delays and reaction–diffusion terms

In this paper, we study the global exponential stability of fuzzy cellular neural networks with delays and reaction–diffusion terms. By constructing a suitable Lyapunov functional and utilizing some inequality techniques, we obtain a sufficient condition for the uniqueness and global exponential stability of the equilibrium solution for a class of fuzzy cellular neural networks with delays and reaction–diffusion terms. The result imposes constraint conditions on the network parameters independently of the delay parameter. The result is also easy to check and plays an important role in the design and application of globally exponentially stable fuzzy neural circuits.     

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.     

Mathematics and Neural Networks –A Glance at some Basic Connections

In the following paper, we present a brief and easily accessible introduction to the theory of neural networks under special emphasis on the rôle of pure and applied mathematics in this interesting field of research. In order to allow a quick and direct approach even for nonspecialists, we only consider three-layer feedforward networks with sigmoidal transfer functions and do not cover general multi-layer, recursive or radial-basis-function networks. Moreover, we focus our attention on density and complexity results while construction problems based on operator techniques are not discussed in detail. Especially, in connection with complexity results, we show that neural networks in general have the power to approximate certain function spaces with a minimal number of free parameters. In other words, under this specific point of view neural networks represent one of the best possible approximation devices available. Besides pointing out this remarkable fact, the main motivation for presenting this paper is to give some more mathematicians an idea of what is going on in the theory of neural networks and, perhaps, to encourage, at least a few of them, to start working in this highly interdisciplinary and promising field, too.     

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.     

EXPONENTIAL STABILITY AND PERIODIC SOLUTION OF HYBRID BIDIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORKS WITH DISCRETE DELAYS

In this paper, we study the existence, uniqueness, and the global exponential stability of the periodic solution and equilibrium of hybrid bidirectional associative memory neural networks with discrete delays. By ingeniously importing real parameters di > 0 (i = 1,2, …, n) which can be adjusted, making use of the Lyapunov functional method and some analysis techniques, some new sufficient conditions are established. Our results generalize and improve the related results in [9]. These conditions can be used both to design globally exponentially stable and periodical oscillatory hybrid bidirectional associative neural networks with discrete delays, and to enlarge the area of designing neural networks. Our work has important significance in related theory and its application.     

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。     

Algebraic signatures of convex and non-convex codes

A convex code is a binary code generated by the pattern of intersections of a collection of open convex sets in some Euclidean space. Convex codes are relevant to neuroscience as they arise from the activity of neurons that have convex receptive fields. In this paper, we develop algebraic methods to determine if a code is convex. Specifically, we use the neural ideal of a code, which is a generalization of the Stanley–Reisner ideal. Using the neural ideal together with its standard generating set, the canonical form, we provide algebraic signatures of certain families of codes that are non-convex. We connect these signatures to the precise conditions on the arrangement of sets that prevent the codes from being convex. Finally, we also provide algebraic signatures for some families of codes that are convex, including the class of intersection-complete codes. These results allow us to detect convexity and non-convexity in a variety of situations, and point to some interesting open questions.     

Hyperbolic sigma-pi neural network operators for compactly supported continuous functions

It is the aim of this contribution to continue our investigations on a special family of hyperbolic-type linear operators (here, for compactly supported continuous functions on IR ⁿ ) which immediately can be interpreted as concrete real-time realizations of three-layer feedforward neural networks with sigma-pi units in the hidden layer. To indicate how these results are connected with density results we start with some introductory theorems on this topic. Moreover, we take a detailed look at the complexity of the generated neural networks in order to achieve global -accuracy.     

Existence and exponential stability of almost periodic solutions for neutral‐type BAM neural networks with distributed leakage delays

This paper is concerned with a class of neutral‐type BAM neural networks with distributed leakage delays. By applying the exponential dichotomy of linear differential equations, Lyapunov functional method and contraction mapping principle, we establish some sufficient conditions which ensure the existence and exponential stability of almost periodic solutions for such BAM neural networks. An example is given to illustrate the effectiveness of the theoretical findings. The results obtained in this article are completely new and complement the previously known studies. Copyright © 2016 John Wiley & Sons, Ltd.     

Coexistence of domains of attraction of nonautonomous neural networks with time-varying delays

This paper presents new dynamical behavior, i.e., the coexistence of 2^N domains of attraction of N-dimensional nonautonomous neural networks with time-varying delays. By imposing some new assumptions on activation functions and system parameters, we construct 2^N invariant basins for neural system and derive some criteria on the boundedness and exponential attractivity for each invariant basin. Particularly, when neural system degenerates into periodic case, we not only attain the coexistence of 2^N periodic orbits in bounded invariant basins but also give their domains of attraction. Moreover, our results are suitable for autonomous neural systems. Our new results improve and generalize former ones. Finally, computer simulation is performed to illustrate the feasibility of our results.     

A neural network to solve quadratic programming problems with fuzzy parameters

In this paper, a representation of a recurrent neural network to solve quadratic programming problems with fuzzy parameters (FQP) is given. The motivation of the paper is to design a new effective one-layer structure neural network model for solving the FQP. As far as we know, there is not a study for the neural network on the FQP. Here, we change the FQP to a bi-objective problem. Furthermore, the bi-objective problem is reduced to a weighting problem and then the Lagrangian dual is constructed. In addition, we consider a neural network model to solve the FQP. Finally, some illustrative examples are given to show the effectiveness of our proposed approach.     

Evaluation of fuzzy regression models by fuzzy neural network

In this paper, a novel hybrid method based on fuzzy neural network for approximate fuzzy coefficients (parameters) of fuzzy linear and nonlinear regression models with fuzzy output and crisp inputs, is presented. Here a neural network is considered as a part of a large field called neural computing or soft computing. Moreover, in order to find the approximate parameters, a simple algorithm from the cost function of the fuzzy neural network is proposed. Finally, we illustrate our approach by some numerical examples.     

Approximating smooth and sparse functions by deep neural networks: Optimal approximation rates and saturation

Constructing neural networks for function approximation is a classical and longstanding topic in approximation theory. In this paper, we aim at constructing deep neural networks with three hidden layers using a sigmoidal activation function to approximate smooth and sparse functions. Specifically, we prove that the constructed deep nets with controllable magnitude of free parameters can reach the optimal approximation rate in approximating both smooth and sparse functions. In particular, we prove that neural networks with three hidden layers can avoid the phenomenon of saturation, i.e., the phenomenon that for some neural network architectures, the approximation rate stops improving for functions of very high smoothness.     

PERIODIC SOLUTIONS AND STABILITY ANALYSIS FOR NEURAL NETWORKS WITH TIME-VARYING DELAY

1 IntroductionIt is well known that both in biological and man-made neural systems, inte-gl.ation afld communication delays are ubiquitous, and often become sources ofinstabilitY' The de1ays in electronic neural networks are usually time varying,and sometimes vary vio1ently with time due to the finite switching speed ofamplifiers and faults in the electrical circuit. They s1ow down the transmissionrate and tend to introduce some degree of instability in circuits. Therefore,fast response must …     

Attractivity,multistability, and bifurcation in delayed Hopfieldʼs model with non-monotonic feedback

For a system of delayed neural networks of Hopfield type, we deal with the study of global attractivity, multistability, and bifurcations. In general, we do not assume monotonicity conditions in the activation functions. For some architectures of the network and for some families of activation functions, we get optimal results on global attractivity. Our approach relies on a link between a system of functional differential equations and a finite-dimensional discrete dynamical system. For it, we introduce the notion of strong attractor for a discrete dynamical system, which is more restrictive than the usual concept of attractor when the dimension of the system is higher than one. Our principal result shows that a strong attractor of a discrete map gives a globally attractive equilibrium of a corresponding system of delay differential equations. Our abstract setting is not limited to applications in systems of neural networks; we illustrate its use in an equation with distributed delay motivated by biological models. We also obtain some results for neural systems with variable coefficients.     

Mean square exponential stability in high-order stochastic impulsive neural networks with time-varying delays

In this paper, we consider a class of stochastic impulsive high-order neural networks with time-varying delays. By using Lyapunov functional method, LMI method and mathematics induction, some sufficient conditions are derived for the globally exponential stability of the equilibrium point of the neural networks in mean square. It is believed that these results are significant and useful for the design and applications of impulsive stochastic high-order neural networks.     

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.     

Approximation on attraction domain of Cohen-Grossberg neural networks

In this paper, approximations of attraction domains of the asymptotically stable equilibrium points of some typical Cohen-Grossberg neural networks are achieved. Most Cohen-Grossberg neural networks are highly nonlinear systems which makes it difficult to approximate their attraction domain. Under some weak assumptions, we are allowed to employ the optimal Lyapunov method to obtain a Lyapunov function for asymptotically stable equilibrium points of a given Cohen-Grossberg neural network. With the help of this Lyapunov function, we approximate the corresponding attraction domain by the iterative expansion approach. Numerical simulations also illustrate that the approximation obtained is really part of the attraction domain.