Asymptotic behavior of a BAM neural network with delays of distributed type

S. Othmani¹ ; N.-E. Tatar² ; A. Khemmoudj¹

¹ Laboratory of SDG, Faculty of Mathematics, University of Science and Technology Houari Boumedienne, P.O. Box 32, El-Alia 16111, Bab Ezzouar, Algiers, Algeria.
² Department of Mathematics and Statistics, King Fahd University of Petroleum and Minerals, 31261 Dhahran, Saudi Arabia.

Mathematical modelling of natural phenomena, Tome 16 (2021), article no. 29.

Résumé

In this paper, we examine a Bidirectional Associative Memory neural network model with distributed delays. Using a result due to Cid [J. Math. Anal. Appl. 281 (2003) 264–275], we were able to prove an exponential stability result in the case when the standard Lipschitz continuity condition is violated. Indeed, we deal with activation functions which may not be Lipschitz continuous. Therefore, the standard Halanay inequality is not applicable. We will use a nonlinear version of this inequality. At the end, the obtained differential inequality which should imply the exponential stability appears ‘state dependent’. That is the usual constant depends in this case on the state itself. This adds some difficulties which we overcome by a suitable argument.

Détail

DOI : 10.1051/mmnp/2021023

Bibliographie

[1] P. Arena, A. Basile, M. Bucolo, L. Fortuna Image processing for medical diagnosis using CNN Nucl. Instruments Methods Phys. Res. Sect. A 2003 174 178

[2] G. Bao, Z. Zeng Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions Neurocomputing 2012 101 107

[3] Z. Cai, L. Huang Existence and global asymptotic stability of periodic solution for discrete and distributed time-varying delayed neural networks with discontinuous activations Neurocomputing 2011 3170 3179

[4] J.A. Cid On uniqueness criteria for systems of ordinary differential equations J. Math. Anal. Appl 2003 264 275

[5] E.Y. Cong, X. Han, X. Zhang Global exponential stability analysis of discrete-time BAM neural networks with delays: A mathematical induction approach Neurocomputing 2020 227 235

[6] B.T. Cui, X.Y. Lou Global asymptotic stability of BAM neural networks with distributed delays and reaction-diffusion terms Chaos Solitons Fractals 2006 1347 1354

[7] M. Forti, M. Grazzini, P. Nistri, L. Pancioni Generalized Lyapunov approach for convergence of neural networks with discontinuous or non-Lipschitz activations Phys. D Nonlinear Phenom 2006 88 99

[8] D. Gao, J. Li Global asymptotic stability of periodic solutions for neutral-type BAM neural networks with delays Neural Process. Lett 2020 367 382

[9] P. Hartman, Ordinary Differential Equations. Wiley, New York (1964).

[10] L. Van Hien, L.D. Hai-An Exponential stability of positive neural networks in bidirectional associative memory model with delays Math. Methods Appl. Sci 2019 6339 6357

[11] Y. Huang, H. Zhang, Z. Wang Dynamical stability analysis of multiple equilibrium points in time-varying delayed recurrent neural networks with discontinuous activation functions Neurocomputing 2012 21 28

[12] M. Iswarya, R. Raja, G. Rajchakit, J. Cao, J. Alzabut, C. Huang Existence, uniqueness and exponential stability of periodic solution for discrete-time delayed bam neural networks based on coincidence degree theory and graph theoretic method Mathematics 2019 1 18

[13] B. Kosko Adaptive bi-directional associative memories Appl. Optim 1987 4947 4960

[14] B. Kosko Bi-directional associative memories IEEE Trans. Syst. Man Cybern 1988 49 60

[15] B. Kosko, Neural networks and Fuzzy systems – a dynamical system approach machine intelligence. Englewood Cliffs, Prentice-Hall (1992) 38–108.

[16] X. Li, J. Jia Global robust stability analysis for BAM neural networks with time-varying delays Neurocomputing 2013 499 503

[17] Y. Li, L. Yang, W. Wu Anti-periodic solution for impulsive BAM neural networks with time-varying leakage delays on time scales Neurocomputing 2015 536 545

[18] B. Liu Global exponential stability for BAM neural networks with time-varying delays in the leakage terms Nonlinear Anal. Real World Appl 2013 559 566

[19] Y. Liu, Z. Wang, X. Liu Global asymptotic stability of generalized bi-directional associative memory networks with discrete and distributed delays Chaos Solitons Fractals 2006 793 803

[20] C. Maharajan, R. Raja, J. Cao, G. Rajchakit, Z. Tu, A. Alsaedi LMI-based results on exponential stability of BAM-type neural networks with leakage and both time-varying delays: A non-fragile state estimation approach Appl. Math. Comput 2018 33 55

[21] G. Mathai, B.R. Upadhyaya Performance analysis and application of the bidirectional associative memory to industrial spectral signatures Proc. IJCNN 1989 33 37

[22] S. Mohamad, K. Gopalsamy, H. Akça Exponential stability of artificial neural networks with distributed delays and large impulses Nonlinear Anal. Real World Appl 2008 872 888

[23] W. Peng, Q. Wu, Z. Zhang LMI-based global exponential stability of equilibrium point for neutral delayed BAM neural networks with delays in leakage terms via new inequality technique Neurocomputing 2016 103 113

[24] Z. Quan, L. Huang, S. Yu, Z. Zhang Novel LMI-based condition on global asymptotic stability for BAM neural networks with reaction-diffusion terms and distributed delays Neurocomputing 2014 213 223

[25] V. Sharma, R. Jha, R. Naresh Optimal multi-reservoir network control by augmented Lagrange programming neural network Appl. Soft Comput. J 2007 783 790

[26] Q. Song Novel criteria for global exponential periodicity and stability of recurrent neural networks with time-varying delays Chaos Solitons Fractals 2008 720 728

[27] N.-E. Tatar Control of systems with Hölder continuous functions in the distributed delays Carpathian J. Math 2014 123 128

[28] N.-E. Tatar Long time behavior for a system of differential equations with non-Lipschitzian nonlinearities Adv. Artificial Neural Network. Syst 2014

[29] N.-E. Tatar Haraux type activation functions in neural network theory Br. J. Math. Math. Computer Sci 2014 3163 3170

[30] N.-E. Tatar Neural networks with delayed Hölder continuous activation functions Int. J. Artificial Intelligence Mech 2014 156 160

[31] N.-E. Tatar Hölder continuous activation functions Adv. Diff. Eqs. Control Processes Neural Netw 2015 93 106

[32] N.-E. Tatar Exponential decay for a system of equations with distributed delays J. Appl. Math 2015

[33] N.-E. Tatar On a general nonlinear problem with distributed delays J. Contemporary Math. Anal 2017 184 190

[34] N.-E. Tatar A nonlinear version of the distributed Halanay inequality and application Submitted.

[35] H. Wu, C. Shan Stability analysis for periodic solution of BAM neural networks with discontinuous neuron activations and impulses Appl. Math. Model 2009 2564 2574

[36] H. Wu, F. Tao, L. Qin, R. Shi, L. He Robust exponential stability for interval neural networks with delays and non-Lipschitz activation functions Nonlinear Dyn 2011 479 487

[37] H. Wu, X. Xue Stability analysis for neural networks with inverse Lipschitzian neuron activations and impulses Appl. Math. Model 2008 2347 2359

[38] C. Xu, P. Li Existence and exponentially stability of anti-periodic solutions for neutral BAM neural networks with time-varying delays in the leakage terms J. Nonlinear Sci. Appl 2016 1285 1305

[39] C. Xu, P. Li, Y. Pang Existence and exponential stability of almost periodic solutions for neutral-type BAM neural networks with distributed leakage delays Math. Methods Appl. Sci 2017 2177 2196

[40] Y. Yao, W.J. Freeman, B. Burke, Q. Yang Pattern recognition by a distributed neural network: an industrial application Neural Netw 1991 103 121

[41] H. Zhao Global stability of bidirectional associative memory neural networks with distributed delays Phys. Lett. A 2002 182 190

[42] H. Zhao Global asymptotic stability of Hopfield neural networks involving distributed delays Neural Networks 2004 47 53

[43] J. Zhou, S. Li, Z. Yang Global exponential stability of Hopfield neural networks with distributed delays Appl. Math. Model 2009 1513 1520