Abstract
We investigate the exponential convergence characteristics of an equilibrium state of a delayed cellular neural network (DCNN) whose state variables are governed by a system of nonlinear integrodifferential equations with delays distributed continuously over unbounded intervals. The network is designed in such a way that the self-connections are inhibitory and instantaneous, and the activation functions are globally Lipschitz continuous and they are not necessarily bounded and differentiable. While monotonicity is generally not required for the activation functions, it is however needed for the activations of the inhibitory and instantaneous self-connections. By applying a Young inequality to an appropriate form of Lyapunov functionals, we establish the exponential convergence of the network towards a unique equilibrium state under a set of easily verifiable and delay independent sufficient conditions. It is shown that the restriction holding between the neural parameter values can be relaxed by the presence of the inhibitory and instantaneous self-connections and the corresponding monotonically increasing activation functions. The global exponential stability results obtained in this article will improve and extend the existing results which have been published in the literature on neural networks.
Results in this paper were presented at the International Conference on Mathematical Modelling and Computation held at the University of Brunei Darussalam during 5–8 June 2006. in conjunction with the 20th anniversary celebration of the foundation of the university.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
S. Arik, An improved global stability result for delayed cellular neural networks, IEEE Trans. Circ. Syst.-I 49 (2002), 1211–1214.
G. Avitabile, M. Forti, S. Manetti, M. Marini, On a class of nonsymmetrical neural networks with application to ADC, IEEE Trans. Circuits Syst. 38 (1991), 202–209.
E. F. Beckenbach, R. Bellman, Inequalities, Springer Verlag, New York, 1965.
J. Cao, New results concerning exponential stability and periodic solutions of delayed cellular neural networks, Phys. Lett. A 307 (2003), 136–147.
J. Cao, Global exponential stability and periodic solutions of delayed cellular neural networks, J. Comp. Syst. Sci. 60 (2000), 38–46.
J. Cao, On exponential stability and periodic solutions of CNN’s with delays, Phys. Lett. A 267 (2000), 312–318.
J. Cao, Q. Li, On the exponential stability and periodic solutions of delayed cellular neural networks, J. Math. Anal. Appl. 252 (2000), 50–64.
J. Cao, Global stability analysis in delayed cellular neural networks, Phys. Rev. E 59 (1999), 5940–5944.
J. Cao, Periodic solutions and exponential stability in delayed cellular neural networks, Phys. Rev. E 60 (1999), 3244–3248.
J. Cao, On stability of delayed cellular neural networks, Phys. Lett. A 261 (1999), 303–308.
J. Cao, D. Zhou, Stability analysis of delayed cellular neural networks, Neural Networks 11 (1998), 1601–1605.
A. Chen, J. Cao, L. Huang, Global robust stability of interval cellular neural networks with time-varying delays, Chaos Solitons Fractals 23 (2005), 787–799.
A. Chen, J. Cao, L. Huang, Periodic solution and global exponential stability for shunting inhibitory delayed cellular neural networks, Electr. J. Diff. Equ. 2004 (2004), 1–16.
L. O. Chua, T. Roska, Stability of a class of nonreciprocal cellular neural networks, IEEE Trans. Circ. Syst. 37 (1990), 1520–1527.
L. O. Chua, L. Yang, Cellular neural networks: Theory, IEEE Trans. Circ. Syst. 35 (1988), 1257–1272.
L. O. Chua, L. Yang, Cellular neural networks: Applications, IEEE Trans Circ. Syst. 35 (1988), 1273–1290.
P. P. Civalleri, M. Gilli, L. Pandolfi, On stability of cellular neural networks with delay, IEEE Trans. Circ. Syst. I: Fund. Theor. Appl. 40 (1993), 157–165.
M. Forti, A. Tesi, New conditions for global stability of neural networks with application to linear and quadratic programming problems, IEEE Trans. Circuits Syst. I: Fund. Theor. Appl. 42 (1995), 354–366.
M. Forti, On global asymptotic stability of a class of nonlinear systems arising in neural network theory, J. Diff. Equ. 113 (1994), 246–264.
M. Forti, S. Manetti, M. Marini, Necessary and sufficient condition for absolute stability of neural networks, IEEE Trans. Circ. Syst. I: Fund. Theor. Appl. 41 (1994), 491–494.
M. Forti, S. Manetti, M. Marini, A condition for global convergence of a class of symmetric neural circuits, IEEE Trans. Circ. Syst. I: Fund. Theor. Appl. 39 (1992), 480–483.
C. J. Fu, A sufficient condition for exponential stability of cellular neural networks with time-varying delays, J. Math. (Wuhan) 22 (2002), 266–270.
M. Gilli, Stability of cellular neural networks and delayed cellular neural networks with nonpositive templates and nonmonotonic output functions, IEEE Trans. Circ. Syst. I: Fund. Theor. Appl. 41 (1994), 518–528.
K. Gopalsamy, Stability of artificial neural networks with impulses, Appl. Math. Computat. 154 (2004), 783–813.
K. Gopalsamy, X. Z. He, Stability in asymmetric Hopfield nets with transmission delays, Phys. D 76 (1994), 344–358.
K. Gopalsamy, Stability and Oscillations in Delay Differential Equations of Population Dynamics, Kluwer Academic Press, The Netherlands, 1992.
C. Guzelis, L. O. Chua, Stability analysis of generalised cellular neural networks, Int. J. Circuit Theor. Appl. 21 (1993), 1–33.
T. Lara, P. Ecimovciz, J. Wu, Delayed cellular neural networks: model, applications, implementations, and dynamics, Diff. Equ. Dynam. Systems 10 (2002), 71–97.
X. Li, L. Huang, Exponential stability and global stability of cellular neural networks, Appl. Math. Computat. 147 (2004), 843–853.
X. M. Li, L. H. Huang, H. Zhu, Global stability of cellular neural networks with constant and variable delays, Nonlin. Anal. 53 (2003), 319–333.
X.X. Liao, J. Wang, Algebraic criteria for global exponential stability of cellular neural networks with multiple time delays, IEEE Trans. Circuits Systems I Fund. Theory Appl. 50 (2003), 268–275.
X. Liao, Z. Wu, J. Yu, Stability analyses of cellular neural networks with continuous time delay, J. Computat. Appl. Math. 143 (2002), 29–47.
D. Liu, A. N. Michel, Cellular neural networks for associative memories, IEEE Trans. Circ. Syst. II: Analog Dig. Sig. Proc. 40 (1993), 119–121.
Z. Liu, L. Liao, Existence and global exponential stability of periodic solution of cellular neural networks with time-varying delays, J. Math. Anal. Appl. 290 (2004), 247–262.
S. Mohamad, Convergence dynamics of delayed Hopfield-type neural networks under almost periodic stimuli, Acta Appl. Math. 76 (2003), 117–135.
S. Mohamad, Global exponential stability in discrete-time analogues of delayed cellular neural networks, J. Differ. Equ. Appl. 9 (2003), 559–575.
S. Mohamad, K. Gopalsamy, Exponential stability of continuous-time and discrete-time cellular neural networks with discrete delays, Appl. Math. Computat. 135 (2003), 17–38.
S. Mohamad, K. Gopalsamy, Dynamics of a class of discrete-time neural networks and their continuous-time counterparts, Math. Comput. Simul. 53 (2000), 1–39.
T. Roska, L. Chua, D. Wolf, T. Kozek, R. Tetzlaff, F. Puffer, Simulating nonlinear waves and PDEs via CNN — Part I: Basic Techniques, Part II: Typical examples, IEEE Trans. Circuits Systems-I 42 (1995), 809–820.
T. Roska, W. Chai, L. Chua, Stability of CNN with dominant nonlinear and delay-type templates, IEEE Trans. Circuits Systems-I 40 (1993), 270–272.
T. Roska, L. O. Chua, Cellular neural networks with nonlinear and delay-type template elements, Int. J. Circuit Theory Appl. 20 (1992), 469–481.
T. Sasagawa, Sufficient condition for the exponential p-stability and p-stabilizability of linear stochastic systems, Int. J. Syst. Sci. 13 (1982), 399–408.
A. Slavova, Cellular neural network models of some equations from Biology, Physics and Ecology, Funct. Diff. Equ. 10 (2003), 579–591.
A. Slavova, Applications of some mathematical methods in the analysis of cellular neural networks, J. Computat. Appl. Math. 114 (2000), 387–404.
N. Takahashi, L. O. Chua, On the complete stability of nonsymmetric cellular neural networks, IEEE Trans. Circuits Syst. I: Fund. Theor. Appl. 45 (1998), 754–758.
N. Takahashi, L. O. Chua, A new sufficient condition for nonsymmetric CNN’s to have a stable equilibrium point, IEEE Trans. Circuits Syst. I: Fund. Theor. Appl. 44 (1997), 1092–1095.
D. W. Tank, J. J. Hopfield, Neural computation by concentrating information in time, Proc. Natl. Acad. Sci. USA 84 (1987), 1896–1990.
H. Xie, Q. Wang, The existence of almost periodic solution for cellular neural networks with variable coefficients and delays, Ann. Diff. Equ. 21 (2005), 65–72.
H. Yanai, S. Amari, Auto-associative memory with two-stage dynamics of nonmonotonic neurons, IEEE Trans. Neural Networks 7 (1996), 803–815.
S. Yoshizawa, M. Morita, S. I. Amari, Capacity of associative memory using a nonmonotonic neuron model, Neural Networks 6 (1993), 167–176.
J. Zhang, Absolute stability analysis in cellular neural networks with variable delays and unbounded delay, Comp. Math. Appl. 47 (2004) 183–194.
Q. Zhang, X. Wei, J. Xu, New stability conditions for neural networks with constant and variable delays, Chaos Solitons Fractals 26 (2005), 1391–1398.
Q. Zhang, X. Wei, J. Xu, On global exponential stability of nonautonomous delayed neural networks, Chaos Solitons Fractals 26 (2005), 965–970.
Q. Zhang, X. Wei, J. Xu, Delay-dependent exponential stability of cellular neural networks with time-varying delays, Chaos Solitons Fractals 23 (2005) 1363–1369.
H. Zhao, Existence and global attractivity of almost periodic solution for cellular neural network with distributed delays, Appl. Math. Computat. 154 (2004), 683–695.
D. Zhou, L. Zhang, J. Cao, On global exponential stability of cellular neural networks with Lipschitz-continuous activation function and variable delays, Appl. Math. Comput. 151 (2004), 379–392.
D. Zhou, J. Cao, Globally exponential stability conditions for cellular neural networks with time-varying delays, Appl. Math. Computat. 131 (2002), 487–496.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Birkhäuser Verlag Basel/Switzerland
About this chapter
Cite this chapter
Mohamad, S. (2008). Exponential Convergence Analysis of DCNNs having Unbounded Activations and Inhibitory Self-Connections. In: Hosking, R.J., Venturino, E. (eds) Aspects of Mathematical Modelling. Mathematics and Biosciences in Interaction. Birkhäuser Basel. https://doi.org/10.1007/978-3-7643-8591-0_14
Download citation
DOI: https://doi.org/10.1007/978-3-7643-8591-0_14
Publisher Name: Birkhäuser Basel
Print ISBN: 978-3-7643-8590-3
Online ISBN: 978-3-7643-8591-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)