Complete stability of delayed recurrent neural networks with Gaussian activation functions

This paper addresses the complete stability of delayed recurrent neural networks with Gaussian activation functions. By means of the geometrical properties of Gaussian function and algebraic properties of nonsingular M-matrix, some sufficient conditions are obtained to ensure that for an n-neuron neural network, there are exactly 3k equilibrium points with 0≤k≤n, among which 2k and 3k-2k equilibrium points are locally exponentially stable and unstable, respectively. Moreover, it concludes that all the states converge to one of the equilibrium points; i.e., the neural networks are completely stable. The derived conditions herein can be easily tested. Finally, a numerical example is given to illustrate the theoretical results.

[1]  CHIH-WEN SHIH,et al.  Multistability in Recurrent Neural Networks , 2006, SIAM J. Appl. Math..

[2]  Zhigang Zeng,et al.  Circuit design and exponential stabilization of memristive neural networks , 2015, Neural Networks.

[3]  Tianping Chen,et al.  Complete stability of cellular neural networks with unbounded time-varying delays , 2012, Neural Networks.

[4]  Zhigang Zeng,et al.  Multistability of Recurrent Neural Networks With Nonmonotonic Activation Functions and Mixed Time Delays , 2016, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[5]  Buse Melis Ozyildirim,et al.  Generalized classifier neural network , 2013, Neural Networks.

[6]  Jinde Cao,et al.  Robust Exponential Stability of Markovian Jump Impulsive Stochastic Cohen-Grossberg Neural Networks With Mixed Time Delays , 2010, IEEE Transactions on Neural Networks.

[7]  Narasimhan Sundararajan,et al.  Projection-Based Fast Learning Fully Complex-Valued Relaxation Neural Network , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Zhigang Zeng,et al.  Multistability of Neural Networks With Time-Varying Delays and Concave-Convex Characteristics , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Zhigang Zeng,et al.  Multistability of Two Kinds of Recurrent Neural Networks With Activation Functions Symmetrical About the Origin on the Phase Plane , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Najdan Vukovic,et al.  A growing and pruning sequential learning algorithm of hyper basis function neural network for function approximation , 2013, Neural Networks.

[12]  Zhigang Zeng,et al.  Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions , 2012, Neurocomputing.

[13]  Zhigang Zeng,et al.  Memory pattern analysis of cellular neural networks , 2005 .

[14]  Chih-Wen Shih,et al.  Complete Stability in Multistable Delayed Neural Networks , 2009, Neural Computation.

[15]  Sue Ann Campbell,et al.  Stability, Bifurcation, and Multistability in a System of Two Coupled Neurons with Multiple Time Delays , 2000, SIAM J. Appl. Math..

[16]  Ryotaro Kamimura.  Cooperative information maximization with Gaussian activation functions for self-organizing maps , 2006, IEEE Trans. Neural Networks.

[17]  Tianping Chen,et al.  Multiple µ-stability of neural networks with unbounded time-varying delays , 2014, Neural Networks.

[18]  Chih-Wen Shih,et al.  Multistability for Delayed Neural Networks via Sequential Contracting , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Zhigang Zeng,et al.  Stability analysis of delayed cellular neural networks described using cloning templates , 2004, IEEE Trans. Circuits Syst. I Regul. Pap..

[20]  Tianping Chen,et al.  Coexistence and local stability of multiple equilibria in neural networks with piecewise linear nondecreasing activation functions , 2010, Neural Networks.

[21]  Mauro Forti,et al.  Necessary and sufficient condition for multistability of neural networks evolving on a closed hypercube , 2014, Neural Networks.

[22]  Wei Xing Zheng,et al.  On Extended Dissipativity of Discrete-Time Neural Networks With Time Delay , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[23]  Jinde Cao,et al.  Multistability of Second-Order Competitive Neural Networks With Nondecreasing Saturated Activation Functions , 2011, IEEE Transactions on Neural Networks.

[24]  Eva Kaslik,et al.  Multistability in impulsive hybrid Hopfield neural networks with distributed delays , 2011 .

[25]  Jinde Cao,et al.  Stability Analysis of Markovian Jump Stochastic BAM Neural Networks With Impulse Control and Mixed Time Delays , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Zhigang Zeng,et al.  Complete stability of cellular neural networks with time-varying delays , 2006, IEEE Transactions on Circuits and Systems I: Regular Papers.

[27]  Huaguang Zhang,et al.  Dynamical stability analysis of multiple equilibrium points in time-varying delayed recurrent neural networks with discontinuous activation functions , 2012, Neurocomputing.

[28]  S. Arik.  Stability analysis of delayed neural networks , 2000 .

[29]  Tianping Chen,et al.  Multistability of Neural Networks With Mexican-Hat-Type Activation Functions , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[30]  Shengyuan Xu,et al.  Stability Analysis of Distributed Delay Neural Networks Based on Relaxed Lyapunov–Krasovskii Functionals , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[31]  Hong Chen,et al.  Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks , 1993, IEEE Trans. Neural Networks.

[32]  Chin-Teng Lin,et al.  Generalized EEG-Based Drowsiness Prediction System by Using a Self-Organizing Neural Fuzzy System , 2012, IEEE Transactions on Circuits and Systems I: Regular Papers.

[33]  Qing-Long Han,et al.  New Lyapunov-Krasovskii Functionals for Global Asymptotic Stability of Delayed Neural Networks , 2009, IEEE Trans. Neural Networks.

[34]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[35]  Wei Xing Zheng,et al.  A New Method for Complete Stability Analysis of Cellular Neural Networks With Time Delay , 2010, IEEE Transactions on Neural Networks.

[36]  Huaguang Zhang,et al.  A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[37]  Wei Xing Zheng,et al.  Multistability of neural networks with discontinuous non-monotonic piecewise linear activation functions and time-varying delays , 2015, Neural Networks.

[38]  Jinde Cao,et al.  Exponential Stability of Stochastic Neural Networks With Both Markovian Jump Parameters and Mixed Time Delays , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[39]  Jinde Cao,et al.  Exponential input-to-state stability of stochastic Cohen–Grossberg neural networks with mixed delays , 2014, Nonlinear Dynamics.

[40]  Zhigang Zeng,et al.  Multistability analysis of a general class of recurrent neural networks with non-monotonic activation functions and time-varying delays , 2016, Neural Networks.

[41]  Sundaram Suresh,et al.  Metacognitive Learning in a Fully Complex-Valued Radial Basis Function Neural Network , 2012, Neural Computation.

[42]  Alberto Tesi,et al.  A New Method to Analyze Complete stability of PWL Cellular Neural Networks , 2001, Int. J. Bifurc. Chaos.

[43]  Huai-Ning Wu,et al.  Synchronization and Adaptive Control of an Array of Linearly Coupled Reaction-Diffusion Neural Networks With Hybrid Coupling , 2014, IEEE Transactions on Cybernetics.

[44]  Chein-I Chang,et al.  Robust radial basis function neural networks , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[45]  Tianping Chen,et al.  Multistability and complete convergence analysis on high-order neural networks with a class of nonsmooth activation functions , 2015, Neurocomputing.

[46]  Sukhan Lee,et al.  A Gaussian potential function network with hierarchically self-organizing learning , 1991, Neural Networks.

[47]  Mauro Forti.  Some extensions of a new method to analyze complete stability of neural networks , 2002, IEEE Trans. Neural Networks.

[48]  Yoh-Han Pao,et al.  Stochastic choice of basis functions in adaptive function approximation and the functional-link net , 1995, IEEE Trans. Neural Networks.

[49]  C. Moraga,et al.  A cosine-modulated Gaussian activation function for hyper-hill neural networks , 1996, Proceedings of Third International Conference on Signal Processing (ICSP'96).

[50]  Chang-Yuan Cheng,et al.  Multistability and convergence in delayed neural networks , 2007 .