##
**Almost periodicity for a class of delayed Cohen-Grossberg neural networks with discontinuous activations.**
*(English)*
Zbl 1258.92002

Summary: The objective of this paper is to investigate the dynamics of a class of delayed Cohen-Grossberg neural networks with discontinuous neuron activations. By means of retarded differential inclusions, we obtain a result on the local existence of solutions, which improves the previous related results for delayed neural networks. It is shown that an M-matrix condition satisfied by the neuron interconnections, can guarantee not only the existence and uniqueness of an almost periodic solution, but also its global exponential stability. It is also shown that the \(M\)-matrix condition ensures that all solutions of the system display a common asymptotic behavior. We prove that the existence interval of the almost periodic solution is \((-\infty , +\infty )\), whereas the existence interval is only proved to be \([0, +\infty )\) in most of the literature. As special cases, we derive results of existence, uniqueness and global exponential stability of a periodic solution for delayed neural networks with periodic coefficients, as well as the similar results of an equilibrium for the systems with constant coefficients. To the author’s knowledge, the results in this paper are the only available results on almost periodicity for Cohen-Grossberg neural networks with discontinuous activations and delays.

### MSC:

92B20 | Neural networks for/in biological studies, artificial life and related topics |

34K14 | Almost and pseudo-almost periodic solutions to functional-differential equations |

39A24 | Almost periodic solutions of difference equations |

PDF
BibTeX
XML
Cite

\textit{J. Wang} and \textit{L. Huang}, Chaos Solitons Fractals 45, No. 9--10, 1157--1170 (2012; Zbl 1258.92002)

Full Text:
DOI

### References:

[1] | Allegretto, W.; Papini, D.; Forti, M., Common asymptotic behavior of solutions and almost periodicity for discontinuous, delayed, and impulsive neural networks, IEEE Trans Neural Networ, 21, 1110-1125 (2010) |

[2] | Aubin, J. P.; Cellina, A., Differential inclusions (1984), Springer: Springer Berlin |

[3] | Cao, J., Periodic oscillation and exponential stability of delayed CNNs, Phys Lett A, 270, 157-163 (2000) |

[4] | Cao, J.; Chen, T., Globally exponentially robust stability and periodicity of delayed neural networks, Chaos Soliton Fract, 22, 4, 957-963 (2004) · Zbl 1061.94552 |

[5] | Cao, J.; Li, X., Stability in delayed Cohen-Grossberg neural networks: LMI optimization approach, Physica D, 212, 54-65 (2005) · Zbl 1097.34053 |

[6] | Cao, J.; Wang, L., Exponential stability and periodic oscillatory solution in BAM networks with delay, IEEE Trans Neural Networ, 13, 457-463 (2002) |

[7] | Chen, T.; Rong, L., Delay-independent stability analysis of Cohen-Grossberg neural networks, Phys Lett A, 317, 436-449 (2003) · Zbl 1030.92002 |

[8] | Chen, T.; Wang, L.; Ren, C., Existence and global stability analysis of almost periodic solutions for Cohen-Grossberg neural networks, Lect Notes Comput Sci, 3971, 204-210 (2006) |

[9] | Chen, X.; Song, Q., Global exponential stability of the periodic solution of delayed Cohen-Grossberg neural networks with discontinuous activations, Neurocomputing, 73, 3097-3104 (2010) · Zbl 1197.34084 |

[10] | Chong, E. K.P.; Hui, S.; Zak, S. H., An analysis of a class of neural networks for solving linear programming problems, IEEE Trans Automat Control, 44, 11, 1095-2006 (1999) · Zbl 0957.90087 |

[11] | Chua, L. O.; Yang, L., Cellular neural networks: theory, IEEE Trans Circuits Syst I, 35, 10, 1257-1272 (1988) · Zbl 0663.94022 |

[12] | Clarke, F. H., Optimization and nonsmooth analysis (1983), Wiley: Wiley New York · Zbl 0727.90045 |

[13] | Cohen, M. A.; Grossberg, S., Absolute stability and global pattern formation and parallel memory storage by competitive neural networks, IEEE Trans Syst Man Cybernet, 13, 815-826 (1983) · Zbl 0553.92009 |

[14] | Filippov, A. F., Differential equations with discontinuous righthand sides (1988), Kluwer Academic Publishers · Zbl 0664.34001 |

[15] | Forti, M., M-matrices and global convergence of discontinuous neural networks, Int J Circuits Theor Appl, 35, 105-130 (2007) · Zbl 1131.92004 |

[16] | Forti, M.; Grazzini, M.; Nistri, P.; Pancioni, L., Generalized Lyapunov approach for convergence of neural networks with discontinuous or non-Lipschitz activations, Physica D, 214, 88-99 (2006) · Zbl 1103.34044 |

[17] | Forti, M.; Nistri, P., Global convergence of neural networks with discontinuous neuron activations, IEEE Trans Circuits Syst I, 50, 11, 1421-1435 (2003) · Zbl 1368.34024 |

[18] | Forti, M.; Nistri, P.; Papini, D., Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain, IEEE Trans Neural Networ, 16, 6, 1449-1643 (2005) |

[19] | Forti, M.; Nistri, P.; Quincampoix, M., Generalized neural network for nonsmooth nonlinear programming problems, IEEE Trans Circuits Syst I, 51, 9, 1741-1754 (2004) · Zbl 1374.90356 |

[20] | Haddad, G., Monotone viable trajectories for functional differential inclusions, J Differ Equat, 42, 1-24 (1981) · Zbl 0472.34043 |

[22] | Hershkowitz, D., Recent directions in matrix stability, Linear Algebra Appl, 171, 161-186 (1992) · Zbl 0759.15010 |

[23] | Hirsch, M., Convergent activation dynamics in continuous time networks, Neural Networ, 2, 331-349 (1989) |

[24] | Hopfield, J. J., Neurons with graded response have collective computational properties like those of two-state neurons, Proc Natl Acad Sci, 81, 3088-3092 (1984) · Zbl 1371.92015 |

[25] | Hopfield, J. J.; Tank, D. W., Computing with neural circuits: a model, Science, 233, 625-633 (1986) · Zbl 1356.92005 |

[26] | Huang, L.; Guo, Z., Global convergence of periodic solution of neural networks with discontinuous activation functions, Chaos Soliton Fract, 42, 2351-2356 (2009) · Zbl 1198.34096 |

[27] | Huang, L.; Wang, J.; Zhou, X., Existence and global asymptotic stability of periodic solutions for Hopfield neural networks with discontinuous activations, Nonlinear Anal Real World Appl, 10, 1651-1661 (2009) · Zbl 1160.92002 |

[28] | Levitan, B. M.; Zhikov, V. V., Almost periodic functions and differential equations (1982), Cambridge University Press: Cambridge University Press Cambridge · Zbl 0499.43005 |

[29] | Li, L.; Huang, L., Dynamical behaviors of a class of recurrent neural networks with discontinuous neuron activations, Appl Math Model, 33, 4326-4336 (2009) · Zbl 1178.37126 |

[30] | Li, Y., Global exponential stability of BAM neural networks with delays and impulses, Chaos Soliton Fract, 24, 279-285 (2005) · Zbl 1099.68085 |

[31] | Li, Y.; Xing, W.; Lu, L., Existence and global exponential stability of periodic solution of a class of neural networks with impulses, Chaos Soliton Fractal, 27, 437-445 (2006) · Zbl 1084.68103 |

[32] | Liu, X.; Cao, J., On periodic solutions of neural networks via differential inclusions, Neural Networ, 22, 329-334 (2009) · Zbl 1335.93058 |

[33] | Lu, W.; Chen, T., Dynamical behaviors of Cohen-Grossberg neural networks with discontinuous activation functions, Neural Networ, 18, 231-242 (2005) · Zbl 1078.68127 |

[34] | Lu, W.; Chen, T., Dynamical behaviors of delayed neural network systems with discontinuous activation functions, Neural Comput, 18, 683-708 (2006) · Zbl 1094.68625 |

[35] | Lu, W.; Chen, T., Almost periodic dynamics of a class of delayed neural networks with discontinuous activations, Neural Comput, 20, 4, 1065-1090 (2008) · Zbl 1146.68422 |

[36] | Meng, Y.; Huang, L.; Guo, Z.; Hu, Q., Stability analysis of Cohen-Grossberg neural networks with discontinuous neuron activations, Appl Math Model, 34, 358-365 (2010) · Zbl 1185.34106 |

[37] | Mohamad, S., Exponential stability in Hopfield-type neural networks with impulses, Chaos Soliton Fract, 32, 456-467 (2007) · Zbl 1143.34031 |

[38] | Papini, D.; Taddei, V., Global exponential stability of the periodic solution of a delayed neural network with discontinuous activations, Phys Lett A, 343, 1-3, 117-128 (2005) · Zbl 1194.34131 |

[39] | Song, Q.; Cao, J., Stability analysis of Cohen-Grossberg neural networks with both time-varying and continuously distributed delays, J Comput Appl Math, 197, 188-203 (2006) · Zbl 1108.34060 |

[40] | Tank, D. W.; Hopfield, J. J., Simple neural optimization networks: an A/D converter, signal decision circuit, and a linear programming circuit, IEEE Trans Circuits Syst I, 33, 533-541 (1986) |

[41] | Wang, J.; Huang, L.; Guo, Z., Global asymptotic stability of neural networks with discontinuous activations, Neural Networ, 22, 931-937 (2009) · Zbl 1338.93317 |

[42] | Wu, H., Global stability analysis of a general class of discontinuous neural networks with linear growth activation functions, Inform Sci, 179, 3432-3441 (2009) · Zbl 1181.34063 |

[43] | Wu, H.; Shan, C., Stability analysis for periodic solution of BAM neural networks with discontinuous neuron activations and impulses, Appl Math Model, 33, 2564-2574 (2009) · Zbl 1205.34017 |

[44] | Xia, Y.; Cao, J.; Huang, Z., Existence and exponential stability of almost periodic solution for shunting inhibitory cellular neural networks with impulses, Chaos Soliton Fract, 34, 1599-1607 (2007) · Zbl 1152.34343 |

[45] | Xia, Y.; Cao, J.; Lin, M., New results on the existence and uniqueness of almost periodic solution for BAM neural networks with continuously distributed delays, Chaos Soliton Fract, 31, 928-936 (2007) · Zbl 1137.68052 |

[46] | Xiong, W.; Zhou, Q.; Xiao, B.; Yu, Y., Global exponential stability of cellular neural networks with mixed delays and impulses, Chaos Soliton Fract, 34, 896-902 (2007) · Zbl 1137.34358 |

[47] | Yoshizawa, T., Stability theory and the existence of periodic solutions and almost periodic solutions (1975), Springer-Verlag: Springer-Verlag Berlin · Zbl 0304.34051 |

This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.