Multistability of Almost Periodic Solution for Memristive Cohen-Grossberg Neural Networks With Mixed Delays

This paper presents the multistability analysis of almost periodic state solutions for memristive Cohen–Grossberg neural networks (MCGNNs) with both distributed delay and discrete delay. The activation function of the considered MCGNNs is generalized to be nonmonotonic and nonpiecewise linear. It is shown that the MCGNNs with <inline-formula> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula>-neuron have <inline-formula> <tex-math notation="LaTeX">$(K+1)^{n}$ </tex-math></inline-formula> locally exponentially stable almost periodic solutions, where nature number <inline-formula> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> depends on the geometrical structure of the considered activation function. Compared with the previous related works, the number of almost periodic state solutions of the MCGNNs is extensively increased. The obtained conclusions in this paper are also capable of studying the multistability of equilibrium points or periodic solutions of the MCGNNs. Moreover, the enlarged attraction basins of attractors are estimated based on original partition. Some comparisons and convincing numerical examples are provided to substantiate the superiority and efficiency of obtained results.

[1]  Zhigang Zeng,et al.  Global exponential synchronization of memristor-based recurrent neural networks with time-varying delays , 2013, Neural Networks.

[2]  Masahiko Morita,et al.  Associative memory with nonmonotone dynamics , 1993, Neural Networks.

[3]  Jinde Cao,et al.  Exponential Synchronization of Memristive Neural Networks With Delays: Interval Matrix Method , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Yi Wang,et al.  Multiplicity of almost periodic solutions for multidirectional associative memory neural network with distributed delays , 2016, Neurocomputing.

[5]  Tianping Chen,et al.  Multistability and New Attraction Basins of Almost-Periodic Solutions of Delayed Neural Networks , 2009, IEEE Transactions on Neural Networks.

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

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

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

[9]  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.

[10]  Sitian Qin,et al.  Convergence and attractivity of memristor-based cellular neural networks with time delays , 2015, Neural Networks.

[11]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[12]  Mauro Forti,et al.  Multistability of delayed neural networks with hard-limiter saturation nonlinearities , 2018, Neurocomputing.

[13]  Lihong Huang,et al.  Almost periodic dynamical behaviors for generalized Cohen-Grossberg neural networks with discontinuous activations via differential inclusions , 2014, Commun. Nonlinear Sci. Numer. Simul..

[14]  Yan Wang,et al.  A novel memristive Hopfield neural network with application in associative memory , 2017, Neurocomputing.

[15]  Qiankun Song,et al.  Multistability Analysis of Quaternion-Valued Neural Networks With Time Delays , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Calin-Adrian Popa,et al.  Multistability and multiperiodicity in impulsive hybrid quaternion-valued neural networks with mixed delays , 2018, Neural Networks.

[17]  Yang Liu,et al.  Existence and global exponential stability of almost periodic solutions to Cohen-Grossberg neural networks with distributed delays on time scales , 2014, Neurocomputing.

[18]  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.

[19]  Lihong Huang,et al.  Periodicity and multi-periodicity of generalized Cohen–Grossberg neural networks via functional differential inclusions , 2016 .

[20]  Zhigang Zeng,et al.  Multistability of periodic delayed recurrent neural network with memristors , 2012, Neural Computing and Applications.

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

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

[23]  Bruno Crespi,et al.  Storage capacity of non-monotonic neurons , 1999, Neural Networks.

[24]  L. Chua.  Memristor-The missing circuit element , 1971 .

[25]  Zhen Zhou,et al.  Memristor-based 3D neuromorphic computing system and its application to associative memory learning , 2017, 2017 IEEE 17th International Conference on Nanotechnology (IEEE-NANO).

[26]  D. Stewart,et al.  The missing memristor found , 2008, Nature.

[27]  Qiang Ma,et al.  Exponential Stability of Periodic Solution for Impulsive Memristor-Based Cohen-Grossberg Neural Networks with Mixed Delays , 2017, Int. J. Pattern Recognit. Artif. Intell..

[28]  Wei Xing Zheng,et al.  Dynamical Behaviors of Multiple Equilibria in Competitive Neural Networks With Discontinuous Nonmonotonic Piecewise Linear Activation Functions , 2016, IEEE Transactions on Cybernetics.

[29]  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.

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

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

[32]  Changjin Xu,et al.  Exponential Stability of Almost Periodic Solutions for Memristor-Based Neural Networks with Distributed Leakage Delays , 2016, Neural Computation.

[33]  Vittorio Murino,et al.  Structured neural networks for pattern recognition , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[34]  Chih-Wen Shih,et al.  Multiple Almost Periodic Solutions in Nonautonomous Delayed Neural Networks , 2007, Neural Computation.

[35]  Peng Wang,et al.  Global exponential stability of almost periodic solution of delayed neural networks with discontinuous activations , 2013, Inf. Sci..