Multistability analysis of competitive neural networks with Gaussian-wavelet-type activation functions and unbounded time-varying delays

Abstract This paper investigates the coexistence and local stability of multiple equilibrium points for competitive neural networks, where the Gaussian-wavelet-type activation functions are employed and the unbounded time-varying delays are considered. Based on geometric formulation, the fixed point theorem, contraction mapping theorem and rigorous mathematical analysis, a series of sufficient conditions are derived to ascertain that the addressed neural networks have exactly 5n equilibrium points, among which 3n equilibrium points are locally stable. On this basis, some criteria are also obtained on the multiple exponential stability, multiple power stability and multiple log-stability of Hopfield neural networks with Gaussian-wavelet-type activation functions. The obtained results generalize and improve the existing multistability results of Hopfield neural networks and competitive neural networks without time delays and with Gaussian-wavelet-type activation functions. Moreover, it is highlighted that the competitive neural networks with Gaussian-wavelet-type activation functions can have both more total equilibrium points and more locally stable equilibrium points than the ones with Mexican-hat-type activation function. Finally, two numerical examples with computer simulations are provided to illustrate and validate the theoretical results.

[1]  Zhigang Zeng,et al.  Multistability of Recurrent Neural Networks With Nonmonotonic Activation Functions and Unbounded Time-Varying Delays , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Morris W. Hirsch,et al.  Convergent activation dynamics in continuous time networks , 1989, Neural Networks.

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

[4]  Jinde Cao,et al.  Multistability of competitive neural networks with time-varying and distributed delays , 2009 .

[5]  Mauro Forti,et al.  Long transient oscillations in a class of cooperative cellular neural networks , 2015, Int. J. Circuit Theory Appl..

[6]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[7]  Jinde Cao,et al.  Coexistence and local μ-stability of multiple equilibrium points for memristive neural networks with nonmonotonic piecewise linear activation functions and unbounded time-varying delays , 2016, Neural Networks.

[8]  Qiankun Song,et al.  Boundedness and Complete Stability of Complex-Valued Neural Networks With Time Delay , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Jinde Cao,et al.  Multistability and Instability of Competitive Neural Networks with Mexican-Hat-Type Activation Functions , 2014 .

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

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

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

[13]  Eva Kaslik,et al.  Impulsive hybrid discrete-time Hopfield neural networks with delays and multistability analysis , 2011, Neural Networks.

[14]  Zhenjiang Zhao,et al.  Multistability of complex-valued neural networks with time-varying delays , 2017, Appl. Math. Comput..

[15]  Qiankun Song,et al.  Multistability in Networks With Self-Excitation and High-Order Synaptic Connectivity , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[16]  Wei Xing Zheng,et al.  Complete Stability of Neural Networks With Nonmonotonic Piecewise Linear Activation Functions , 2015, IEEE Transactions on Circuits and Systems II: Express Briefs.

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

[18]  Zhang Yi,et al.  Activity Invariant Sets and Exponentially Stable Attractors of Linear Threshold Discrete-Time Recurrent Neural Networks , 2009, IEEE Transactions on Automatic Control.

[19]  Zhigang Zeng,et al.  Multistability of Recurrent Neural Networks With Time-varying Delays and the Piecewise Linear Activation Function , 2010, IEEE Transactions on Neural Networks.

[20]  Jinde Cao,et al.  Multistability and instability of competitive neural networks with non-monotonic piecewise linear activation functions , 2019, Nonlinear Analysis: Real World Applications.

[21]  Jinde Cao,et al.  Multistability and instability of delayed competitive neural networks with nondecreasing piecewise linear activation functions , 2013, Neurocomputing.

[22]  Mauro Forti,et al.  Limit Set Dichotomy and Convergence of Cooperative Piecewise Linear Neural Networks , 2011, IEEE Transactions on Circuits and Systems I: Regular Papers.

[23]  Huaguang Zhang,et al.  Multistability of complex-valued recurrent neural networks with real-imaginary-type activation functions , 2014, Appl. Math. Comput..

[24]  Zhenkun Huang,et al.  Scale-Limited Activating Sets and Multiperiodicity for Threshold-Linear Networks on Time Scales , 2014, IEEE Transactions on Cybernetics.

[25]  Zarita Zainuddin,et al.  Function approximation using artificial neural networks , 2007 .

[26]  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.

[27]  Jinde Cao,et al.  Multistability and multiperiodicity of delayed Cohen–Grossberg neural networks with a general class of activation functions , 2008 .

[28]  Zarita Zainuddin,et al.  AN EFFECTIVE AND NOVEL WAVELET NEURAL NETWORK APPROACH IN CLASSIFYING TYPE 2 DIABETICS , 2012 .

[29]  Tingwen Huang,et al.  Multistability of complex-valued neural networks with discontinuous activation functions , 2016, Neural Networks.

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

[31]  Mauro Forti,et al.  Limit Set Dichotomy and Multistability for a Class of Cooperative Neural Networks With Delays , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[32]  Anke Meyer-Bäse,et al.  Singular Perturbation Analysis of Competitive Neural Networks with Different Time Scales , 1996, Neural Computation.