Abstract
This paper is concerned with a class of neutral-type neural networks with discontinuous activations and time-varying delays. Under the concept of Filippov solution, by applying the differential inclusions and the topological degree theory in set-valued analysis, we employ a novel argument to establish new results on the existence of the periodic solutions for the considered neural networks. After that, we derive some criteria on the uniqueness, global exponential stability of the considered neural networks and convergence of the corresponding autonomous case of the considered neural networks, in terms of nonsmooth analysis theory with Lyapunov-like approach. Without assuming the boundedness (or the growth condition) and monotonicity of the discontinuous neuron activation functions, the results obtained can also be valid. Our results extend previous works on the neutral-type neural networks to the discontinuous cases, some related results in the literature can be enriched and extended. Finally, two typical examples and the corresponding numerical simulations are provided to show the effectiveness and flexibility of the results derived in this paper.
Similar content being viewed by others
References
Aubin JP, Cellina A (1984) Differential inclusions. Springer, Berlin
Berman A, Plemmons RJ (1979) Nonnegative matrices in the mathematical science. Academic press, New York
Clarke FH (1983) Optimization and nonsmooth analysis. Wiley, New York
Cao JD, Wang J (2003) Global asymptotic stability of a general class of recurrent neural networks with time-varying delays. IEEE Trans Circ Syst I 50(1):34–44
Chen XF, Song QK (2010) Global exponential stability of the periodic solution of delayed Cohen-Grossberg neural networks with discontinuous activations. Neurocomputing 73:3097–3104
Cai ZW, Huang LH, Guo ZY, Chen XY (2012) On the periodic dynamics of a class of time-varying delayed neural networks via differential inclusions. Neural Netw 33:97–113
Duan L, Huang LH, Fang XW (2017) Finite-time synchronization for recurrent activations and time-varying delays. Chaos 27:013101
Filippov AF (1988) Mathematics and its applications (Soviet Series), Differential equations with discontinuous right-hand sides. Kluwer Academic Publishers, Boston
Forti M, Nistri P, Papini D (2003) Global convergence of neural networks with discontinuous neuron activations. IEEE Trans Circ Syst I 50(11):1421–1435
Gui Z, Ge W, Yang X (2007) Periodic oscillation for a Hopfield neural networks with neutral delays. Phys Lett A 364:267–273
Guo ZY, Huang LH (2009) Generalized Lyapunov method for discontinuous systems. Nonlinear Anal 71:3083–3092
Hale J (1977) Theory of functional differential equations. Springer, New York
Huang YJ, Zhang HG, Wang ZS (2012) Dynamical stability analysis of multiple equilibrium points in time-varying delayed recurrent neural networks with discontinuous activation functions. Neurocomputing 91:21–28
Komanovskii VB, Nosov VR (1986) Stability of functional differential equations. Academic Press, London
Kuang Y (1993) Delay differential equations with applications in population dynamical system. Academic Press, New York
Kong FC, Lu SP, Luo ZG Solitary wave and periodic wave solutions of generalized neutral-type neural networks with delays. Neural Processing Letters. https://doi.org/10.1007/s11063-017-9747-7
Kong FC, Luo ZG Piecewise pseudo almost periodic solutions of generalized neutral-type neural networks with impulses and delays, Neural Processing Letters. https://doi.org/10.1007/s11063-017-9758-4
Kong FC, Fang XW Pseudo almost periodic solutions of discrete-time neutral-type neural networks with delays, Applied Intelligence. https://doi.org/10.1007/s10489-018-1146-x
Kong FC, Luo ZG (2018) Asymptotic behavior of bounded solutions to a system of neutral functional differential equations in critical case. Appl Math Lett 81:44–49
Lasalle JP (1976) The stability of dynamical system. SIAM, Philadelphia
Lloyd NG (1978) Degree theory: Cambridge tracts in mathematics. Cambridge University press, Cambridge
Li Y, Lin ZH (1995) Periodic solutions of differential inclusions. Nonlinear Anal Theory Methods Appl 24 (5):631–641
Lu WL, Chen TP (2005) Dynamical behaviors of cohenCGrossberg neural networks with discontinuous activation functions. Neural Netw 18(3):231–242
Liu XY, Cao JD (2010) Robust state estimations for neural networks with discontinuous activations. IEEE Trans Syst Man Cybern Part B 40(6):1425–1437
Liu XY, Chen TP, Cao JD, Lu WL (2011) Dissipativity and quasisynchronization for neural networks with discontinuous activations and parameter mismatches. Neural Netw 24:1013–1021
Liu J, Liu XZ, Xie WC (2012) Global convergence of neural networks with mixed time-varying delays and discontinuous neuron activations. Inf Sci 183:92–105
Liu BW (2015) Pseudo almost periodic solutions for neutral type CNNs with continuously distributed leakage delays. Neurocomputing 148:445–454
Mandal S, Majee NC (2011) Existence of periodic solutions for a class of Cohen-Grossberg type neural networks with neutral delays. Neurocomputing 74(6):1000–1007
Nie XB, Cao JD (2012) Existence and global stability of equilibrium point for delayed competitive neural networks with discontinuous activation functions. Int J Syst Sci 43(3):459–474
Papini D, Taddei V (2005) Global exponential stability of the periodic solution of a delayed neural networks with discontinuous activations. Phys Lett A 343:117–128
Wu HQ (2009) Stability analysis for periodic solution of neural networks with discontinuous neuron activations. Nonlinear Anal Real World Appl 10:1717–1729
Wang JF, Huang LH, Guo ZY (2009) Dynamical behaviors of delayed Hopfield neural networks with discontinuous activations. Appl Math Model 33:1793–1802
Wang K, Zhu YL (2010) Stability of almost periodic solution for a generalized neutral-type neural networks with delays. Neurocomputing 73(16):3300–3307
Xiao B (2009) Existence and uniqueness of almost periodic solutions for a class of Hopfield neural networks with neutral delays. Appl Math Lett 22:528–533
Yu YH (2016) Global exponential convergence for a class of HCNNs with neutral time-proportional delays. Appl Math Comput 285:1–7
Yao LG (2017) Global exponential convergence of neutral type shunting inhibitory cellular neural networks with D operator. Neural Process Lett 45(2):401–409
Zhao CH, Wang ZY (2015) Exponential convergence of a SICNN with leakage delays and continuously distributed delays of neutral type. Neural Process Lett 41:239–247
Acknowledgments
We would like to thank the editors and the anonymous reviewers for carefully reading the original manuscript and for the constructive comments and suggestions to improve the presentation of this paper. The research was supported by the National Natural Science Foundation of China (61572035).
Author information
Authors and Affiliations
Contributions
All authors read and approved the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare that they have no competing interests.
Rights and permissions
About this article
Cite this article
Kong, F., Fang, X. & Liang, Z. Dynamic behavior of a class of neutral-type neural networks with discontinuous activations and time-varying delays. Appl Intell 48, 4834–4854 (2018). https://doi.org/10.1007/s10489-018-1240-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-018-1240-0