Anti-periodic solutions for Clifford-valued high-order Hopfield neural networks with state-dependent and leakage delays

Huo, Nina ; Li, Bing ; Li, Yongkun

International Journal of Applied Mathematics and Computer Science, Tome 30 (2020) no. 1, pp. 83-98.

Résumé

A class of Clifford-valued high-order Hopfield neural networks (HHNNs) with state-dependent and leakage delays is considered. First, by using a continuation theorem of coincidence degree theory and the Wirtinger inequality, we obtain the existence of anti-periodic solutions of the networks considered. Then, by using the proof by contradiction, we obtain the global exponential stability of the anti-periodic solutions. Finally, two numerical examples are given to illustrate the feasibility of our results.

Détail

Keywords: Hopfield neural network, anti-periodic solution, coincidence degree, time-varying delay
Mots-clés : sieć neuronowa Hopfielda, stopień koincydencji, opóźnienie czasowo zależne

Bibliographie

[1] Alimi, A.M., Aouiti, C., Chérif, F., Dridi, F. and M’hamdi, M.S. (2018). Dynamics and oscillations of generalized high-order Hopfield neural networks with mixed delays, Neurocomputing 321: 274–295.

[2] Amster, P. (2013). Topological Methods in the Study of Boundary Valued Problems, Springer, New York, NY.

[3] Aouiti, C. (2018). Oscillation of impulsive neutral delay generalized high-order Hopfield neural networks, Neural Computing and Applications 29(9): 477–495.

[4] Aouiti, C., Coirault, P., Miaadi, F. and Moulay, E. (2017). Finite time boundedness of neutral high-order Hopfield neural networks with time delay in the leakage term and mixed time delays, Neurocomputing 260: 378–392.

[5] Bayro-Corrochano, E. and Scheuermann, G. (2010). Geometric Algebra Computing, in Engineering and Computer Science, Springer, London.

[6] Brackx, F., Delanghe, R. and Sommen, F. (1982). Clifford Analysis, Pitman Books Limited, London.

[7] Buchholz, S. (2005). A theory of Neural Computation with Clifford Algebras, PhD thesis, University of Kiel, Kiel.

[8] Buchholz, S., Tachibana, K. and Hitzer, E.M. (2007). Optimal learning rates for Clifford neurons, in J.M. de Sá et al. (Eds), Artificial Neural Networks, Springer, Berlin/Heidelberg, pp. 864–873.

[9] Buchholz, S. and Sommer, G. (2008). On Clifford neurons and Clifford multilayer perceptrons, Neural Networks 21(7): 925–935.

[10] Corrochano, E.B., Buchholz, S. and Sommer, G. (1996). Selforganizing Clifford neural network, IEEE International Conference on Neural Networks, Washington, DC, USA, Vol. 1, pp. 120–125.

[11] Şaylı, M. and Yılmaz, E. (2017). Anti-periodic solutions for state-dependent impulsive recurrent neural networks with time-varying and continuously distributed delays, Annals of Operations Research 258(1): 159–185.

[12] Dorst, L., Fontijne, D. and Mann, S. (2007). Geometric Algebra for Computer Science: An Object-oriented Approach to Geometry, Morgan Kaufmann, Burlington, VA, pp. 609–612.

[13] He, Y., Guoping, L. and David, R. (2007). New delay-dependent stability criteria for neural networks with time-varying delay, IEEE Transactions on Neural Networks 18(1): 310–314.

[14] Hitzer, E., Nitta, T. and Kuroe, Y. (2013). Applications of Clifford’s geometric algebra, Advances in Applied Clifford Algebras 23(2): 377–404.

[15] Hu, J. and Wang, J. (2012). Global stability of complex-valued recurrent neural networks with time-delays, IEEE Transactions on Neural Networks and Learning Systems 23(6): 853–865.

[16] Kan, Y., Lu, J., Qiu, J. and Kurths, J. (2019). Exponential synchronization of time-varying delayed complex-valued neural networks under hybrid impulsive controllers, Neural Networks 114: 157–163.

[17] Ke, Y. and Miao, C. (2017). Anti-periodic solutions of inertial neural networks with time delays, Neural Processing Letters 45(2): 523–538.

[18] Kuroe, Y. (2011). Models of Clifford recurrent neural networks and their dynamics, International Joint Conference on Neural Networks, San Jose, CA, USA, Vol. 3, pp. 1035–1041.

[19] Li, Y., Meng, X. and Xiong, L. (2017). Pseudo almost periodic solutions for neutral type high-order Hopfield neural networks with mixed time-varying delays and leakage delays on time scales, International Journal of Machine Learning and Cybernetics 8(6): 1915–1927.

[20] Li, Y. and Qin, J. (2018). Existence and global exponential stability of periodic solutions for quaternion-valued cellular neural networks with time-varying delays, Neurocomputing 292: 91–103.

[21] Li, Y., Qin, J. and Li, B. (2019a). Anti-periodic solutions for quaternion-valued high-order Hopfield neural networks with time-varying delays, Neural Processing Letters 49(3): 1217–1237.

[22] Li, Y., Qin, J. and Li, B. (2019b). Existence and global exponential stability of anti-periodic solutions for delayed quaternion-valued cellular neural networks with impulsive effects, Mathematical Methods in the Applied Sciences 42(1): 5–23.

[23] Li, Y. and Wang, C. (2013). Existence and global exponential stability of equilibrium for discrete-time fuzzy BAM neural networks with variable delays and impulses, Fuzzy Sets and Systems 217: 62–79.

[24] Li, Y., Wang, H. and Meng, X. (2019c). Almost automorphic synchronization of quaternion-valued high-order Hopfield neural networks with time-varying and distributed delays, IMA Journal of Mathematical Control and Information 36(3): 983–1013.

[25] Li, Y. and Yang, L. (2014). Almost automorphic solution for neutral type high-order Hopfield neural networks with delays in leakage terms on time scales, Applied Mathematics and Computation 242: 679–693.

[26] Liu, Y., Xu, P., Lu, J. and Liang, J. (2016). Global stability of Clifford-valued recurrent neural networks with time delays, Nonlinear Dynamics 84(2): 767–777.

[27] Liu, Y., Zhang, D., Lou, J., Lu, J. and Cao, J. (2018). Stability analysis of quaternion-valued neural networks: Decomposition and direct approaches, IEEE Transactions on Neural Networks and Learning Systems 29(9): 4201–4211.

[28] Liu, Y., Zheng, Y., Lu, J., Cao, J. and Rutkowski, L. (2020). Constrained quaternion-variable convex optimization: A quaternion-valued recurrent neural network approach, IEEE Transactions on Neural Networks and Learning Systems 31(3): 1022–1035, DOI: 10.1109/TNNLS.2019.2916597.

[29] Lou, X. and Cui, B. (2007). Novel global stability criteria for high-order Hopfield-type neural networks with time-varying delays, Journal of Mathematical Analysis and Applications 330(1): 144–158.

[30] Ou, C. (2008). Anti-periodic solutions for high-order Hopfield neural networks, Computers Mathematics with Applications 56(7): 1838–1844.

[31] Pearson, J. and Bisset, D. (1992). Back propagation in a Clifford algebra, in I. Aleksander and J. Taylor (Eds), Artificial Neural Networks, North-Holland, Amsterdam, pp. 413–416.

[32] Pearson, J. and Bisset, D. (2007). Neural networks in the Clifford domain, IEEE International Conference on Neural Networks, Orlando, FL, USA, Vol. 3, pp. 1465–1469.

[33] Rivera-Rovelo, J. and Bayro-Corrochano, E. (2006). Medical image segmentation using a self-organizing neural network and Clifford geometric algebra, International Joint Conference on Neural Networks, Vancouver, Canada, pp. 3538–3545.

[34] Sakthivel, R., Raja, R. and Anthoni, S. (2013). Exponential stability for delayed stochastic bidirectional associative memory neural networks with Markovian jumping and impulses, Journal of Optimization Theory and Applications 150(1): 166–187.

[35] Selvaraj, P., Sakthivel, R. and Kwon, O. (2018). Finite-time synchronization of stochastic coupled neural networks subject to Markovian switching and input saturation, Neural Networks 105: 154–165.

[36] Shi, P. and Dong, L. (2010). Existence and exponential stability of anti-periodic solutions of Hopfield neural networks with impulses, Applied Mathematics and Computation 216(2): 623–630.

[37] Wang, Z., Cao, J., Cai, Z. and Huang, L. (2019). Periodicity and finite-time periodic synchronization of discontinuous complex-valued neural networks, Neural Networks 119: 249–260.

[38] Xiang, H., Yan, K. and Wang, B. (2006). Existence and global exponential stability of periodic solution for delayed high-order Hopfield-type neural networks, Physics Letters A 352(4–5): 341–349.

[39] Xu, B., Liu, X. and Liao, X. (2003). Global asymptotic stability of high-order Hopfield type neural networks with time delays, Computers and Mathematics with Applications 45(10–11): 1729–1737.

[40] Xu, B., Liu, X. and Liao, X. (2006). Global exponential stability of high order Hopfield type neural networks, Applied Mathematics and Computation 174(1): 98–116.

[41] Xu, C. and Li, P. (2017). Pseudo almost periodic solutions for high-order Hopfield neural networks with time-varying leakage delays, Neural Processing Letters 46(1): 41–58.

[42] Zhao, L., Li, Y. and Li, B. (2018). Weighted pseudo-almost automorphic solutions of high-order Hopfield neural networks with neutral distributed delays, Neural Computing and Applications 29(7): 513–527.