Some extensions of a new method to analyze complete stability of neural networks

In a recent work, a new method has been introduced to analyze complete stability of the standard symmetric cellular neural networks (CNNs), which are characterized by local interconnections and neuron activations modeled by a three-segment piecewise-linear (PWL) function. By complete stability it is meant that each trajectory of the neural network converges toward an equilibrium point. The goal of this paper is to extend that method in order to address complete stability of the much wider class of symmetric neural networks with an additive interconnecting structure where the neuron activations are general PWL functions with an arbitrary number of straight segments. The main result obtained is that complete stability holds for any choice of the parameters within the class of symmetric additive neural networks with PWL neuron activations, i.e., such a class of neural networks enjoys the important property of absolute stability of global pattern formation. It is worth pointing out that complete stability is proved for generic situations where the neural network has finitely many (isolated) equilibrium points, as well as for degenerate situations where there are infinite (nonisolated) equilibrium points. The extension in this paper is of practical importance since it includes neural networks useful to solve significant signal processing tasks (e.g., neural networks with multilevel neuron activations). It is of theoretical interest too, due to the possibility of approximating any continuous function (e.g., a sigmoidal function), using PWL functions. The results in this paper confirm the advantages of the method of Forti and Tesi, with respect to LaSalle approach, to address complete stability of PWL neural networks.     

关于神经网络的能量函数

能量函数在神经网络的研究中有着非常重要的作用,人们普遍认为：只要能量函数沿着网络的解是下降的,能量函数的导数为零的点是网络的平衡态,能量函数有下界,则网络是稳定的且网络的平衡态是能量函数的极小点,文中取反例说明上述条件下不能保证网络的稳定性,并取例说明即使网络稳定也不能保证网络的平衡态与能量函数的极小点,证明了在网络具有上述条件的能量函数的情况下网络稳定的充分必要条件是网络的解有界,讨论了网络的平     

Multistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions

This paper studies the multistability of a class of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions. It addresses the nondivergence, global attractivity, and complete stability of the networks. Using the local inhibition, conditions for nondivergence are derived, which not only guarantee nondivergence, but also allow for the existence of multiequilibrium points. Under these nondivergence conditions, global attractive compact sets are obtained. Complete stability is studied via constructing novel energy functions and using the well-known Cauchy Convergence Principle. Examples and simulation results are used to illustrate the theory.     

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

In this paper, the conditions ensuring existence, uniqueness, and global exponential stability of the equilibrium point of a class of neural networks with variable delays are studied. Without assuming global Lipschitz conditions on these activation functions, applying idea of vector Lyapunov function, the sufficient conditions for global exponential stability of neural networks are obtained.     

Complete Convergence of Competitive Neural Networks with Different Time Scales

This paper studies the complete convergence of a class of neural networks with different time scales under the assumption that the activation functions are unsaturated piecewise linear functions. Under this assumption, there are multiple equilibrium points in the neural network. Traditional methods cannot be used in this neural network. Complete convergence is proved by constructing an energy-like function. Simulations are employed to illustrate the theory.     

Global Robust Exponential Stability of Interval General BAM Neural Network with Delays

In this paper, a class of interval general bidirectional associative memory (BAM) neural networks with delays are introduced and studied, which include many well-known neural networks as special cases. By using fixed point technic, we prove an existence and uniqueness of the equilibrium point for the interval general BAM neural networks with delays. By using a proper Lyapunov functions, we get a sufficient condition to ensure the global robust exponential stability for the interval general BAM neural networks with delays, and we just require that activation function is globally Lipschitz continuous, which is less conservative and less restrictive than the monotonic assumption in previous results. In the last section, we also give an example to demonstrate the validity of our stability result for interval neural networks with delays.     

Global Lagrange Stability for Takagi-Sugeno Fuzzy Cohen-Grossberg BAM Neural Networks with Time-varying Delays

This paper concerns the globally exponential stability in Lagrange sense for Takagi-Sugeno (T-S) fuzzy Cohen-Grossberg BAM neural networks with time-varying delays. Based on the Lyapunov functional method and inequality techniques, two different types of activation functions which include both Lipschitz function and general activation functions are analyzed. Several sufficient conditions in linear matrix inequality form are derived to guarantee the Lagrange exponential stability of Cohen-Grossberg BAM neural networks with time-varying delays which are represented by T-S fuzzy models. Finally, simulation results demonstrate the effectiveness of the theoretical results.     

离散Hopfield网络的渐近行为

离散Hopfield神经网络是一类特殊的反馈网络,可广泛应用于联想记忆设计、组合优化计算等方面.反馈神经网络的稳定性不仅被认为是神经网络最基本的问题之一,同时也是神经网络各种应用的基础.为此,利用状态转移方程和定义能量函数的方法,研究离散Hopfield神经网络在部分并行演化模式下的渐近行为,并举例说明了一个已有结论是错误的,同时给出了一些新的网络收敛于稳定状态的充分条件.所获结果进一步推广了一些已有的结论.     

Global stability analysis of a general class of discontinuous neural networks with linear growth activation functions

This paper investigates the global asymptotic stability of the periodic solution for a general class of neural networks whose neuron activation functions are modeled by discontinuous functions with linear growth property. By using Leray-Schauder alternative theorem, the existence of the periodic solution is proved. Based on the matrix theory and generalized Lyapunov approach, a sufficient condition which ensures the global asymptotical stability of a unique periodic solution is presented. The obtained results can be applied to check the global asymptotical stability of discontinuous neural networks with a broad range of activation functions assuming neither boundedness nor monotonicity, and also conform the validity of Forti’s conjecture for discontinuous neural networks with linear growth activation functions. Two illustrative examples are given to demonstrate the effectiveness of the present results.     

Stability analysis of Cohen-Grossberg neural networks

Without assuming boundedness and differentiability of the activation functions and any symmetry of interconnections, we employ Lyapunov functions to establish some sufficient conditions ensuring existence, uniqueness, global asymptotic stability, and even global exponential stability of equilibria for the Cohen-Grossberg neural networks with and without delays. Our results are not only presented in terms of system parameters and can be easily verified and also less restrictive than previously known criteria and can be applied to neural networks, including Hopfield neural networks, bidirectional association memory neural networks, and cellular neural networks.     

Improved conditions for global exponential stability of recurrent neural networks with time-varying delays

This paper presents new theoretical results on global exponential stability of recurrent neural networks with bounded activation functions and time-varying delays. The stability conditions depend on external inputs, connection weights, and time delays of recurrent neural networks. Using these results, the global exponential stability of recurrent neural networks can be derived, and the estimated location of the equilibrium point can be obtained. As typical representatives, the Hopfield neural network (HNN) and the cellular neural network (CNN) are examined in detail.     

On the construction and training of reformulated radial basis function neural networks

Presents a systematic approach for constructing reformulated radial basis function (RBF) neural networks, which was developed to facilitate their training by supervised learning algorithms based on gradient descent. This approach reduces the construction of radial basis function models to the selection of admissible generator functions. The selection of generator functions relies on the concept of the blind spot, which is introduced in the paper. The paper also introduces a new family of reformulated radial basis function neural networks, which are referred to as cosine radial basis functions. Cosine radial basis functions are constructed by linear generator functions of a special form and their use as similarity measures in radial basis function models is justified by their geometric interpretation. A set of experiments on a variety of datasets indicate that cosine radial basis functions outperform considerably conventional radial basis function neural networks with Gaussian radial basis functions. Cosine radial basis functions are also strong competitors to existing reformulated radial basis function models trained by gradient descent and feedforward neural networks with sigmoid hidden units.     

New criteria for globally exponential stability of delayed Cohen–Grossberg neural network

This paper is concerned with analysis problem for the global exponential stability of the Cohen–Grossberg neural networks with discrete delays and with distributed delays. We first prove the existence and uniqueness of the equilibrium point under mild conditions, assuming neither differentiability nor strict monotonicity for the activation function. Then, we employ Lyapunov functions to establish some sufficient conditions ensuring global exponential stability of equilibria for the Cohen–Grossberg neural networks with discrete delays and with distributed delays. Our results are not only presented in terms of system parameters and can be easily verified and also less restrictive than previously known criteria. A comparison between our results and the previous results admits that our results establish a new set of stability criteria for delayed neural networks.     

An energy function for the random neural network

Since Hopfield's seminal work on energy functions for neural networks and their consequence for the approximate solution of optimization problems, much attention has been devoted to neural heuristics for combinatorial optimization. These heuristics are often very time-consuming because of the need for randomization or Monte Carlo simulation during the search for solutions. In this paper, we propose a general energy function for a new neural model, the random neural model of Gelenbe. This model proposes a scheme of interaction between the neurons and not a dynamic equation of the system. Then, we apply this general energy function to different optimization problems.     

Stability and Existence of Periodic Solutions of Periodic Cellular Neural Networks with Time-Vary Delays

By using the continuation theorem of Mawhins coincidence degree theory and constructing a suitable Lyapunov function, some new sufficient conditions are obtained ensuring existence and global asymptotical stability of periodic solution of cellular neural networks with periodic coefficients and delays, which do not require the activation functions to be differentiable and monotone nondecreasing. A numerical example is given to illustrate that the criteria are feasible. These results are helpful to design globally asymptotically stable and periodic oscillatory cellular neural networks.     

Artificial wavelet neuro-fuzzy model based on parallel wavelet network and neural network

From the well-known advantages and valuable features of wavelets when used in neural network, two type of networks (i.e., SWNN and MWNN) have been proposed. These networks are single hidden layer network. Each neuron in the hidden layer is comprised of wavelet and sigmoidal activation functions. First model is derived from adding the outputs of wavelet and sigmoidal activation functions, while in the second model outputs of wavelet and sigmoidal activation function are multiplied together. Using these proposed networks in consequent part of the neuro-fuzzy model, which result summation wavelet neuro-fuzzy and multiplication wavelet neuro-fuzzy models, are also proposed. Different types of wavelet function are tested with proposed networks and fuzzy models on four different types of examples. Convergence of the learning process is also guaranteed by performing stability analysis using Lyapunov function.     

Exponential periodicity and stability of neural networks with reaction-diffusion terms and both variable and unbounded delays

In this paper, the exponential periodicity and stability of neural networks with Lipschitz continuous activation functions are investigated, without assuming the boundedness of the activation functions and the differentiability of time-varying delays, as needed in most other papers. The neural networks contain reaction-diffusion terms and both variable and unbounded delays. Some sufficient conditions ensuring the existence and uniqueness of periodic solution and stability of neural networks with reaction-diffusion terms and both variable and unbounded delays are obtained by analytic methods and inequality technique. Furthermore, the exponential converging index is also estimated. The methods, which does not make use of Lyapunov functional, is simple and valid for the periodicity and stability analysis of neural networks with variable and/or unbounded delays. The results extend some previous results. Two examples are given to show the effectiveness of the obtained results.     

Multistability analysis for recurrent neural networks with unsaturating piecewise linear transfer functions

Multistability is a property necessary in neural networks in order to enable certain applications (e.g., decision making), where monostable networks can be computationally restrictive. This article focuses on the analysis of multistability for a class of recurrent neural networks with unsaturating piecewise linear transfer functions. It deals fully with the three basic properties of a multistable network: boundedness, global attractivity, and complete convergence. This article makes the following contributions: conditions based on local inhibition are derived that guarantee boundedness of some multistable networks, conditions are established for global attractivity, bounds on global attractive sets are obtained, complete convergence conditions for the network are developed using novel energy-like functions, and simulation examples are employed to illustrate the theory thus developed.     

离散时间反馈神经网络的渐近行为研究

Hopfield神经网络是一类应用非常成功的人工神经网络模型，它是研究这个反馈神经网络的基础．该文主要研究离散时间、连续状态的反馈神经网络，它是Hopfield神经网络的推广．众所周知，研究反馈神经网络的稳定性不仅被认为是神经网络最基本、最主要的问题之一，同时也是神经网络各种应用的基础．文中主要研究离散时间反馈神经网络的稳定性，给出了连接权矩阵非对称的并且输入-输出函数是一般的S-函数的新的渐近收敛性条件及相应的收敛性结论．所获结果不仅推广了一些已有的结论，而且为反馈神经网络的应用提供了一定的理论基础．