Stability Analysis of Neutral-Type Hopfield Neural Networks with Discrete Delays

Year 2020, Issue: 19, 515 - 523, 31.08.2020

Özlem Faydasıçok

https://doi.org/10.31590/ejosat.734982

Abstract

This research paper deals with the stability problem for a class of neutral-type Hopfield neural networks that involves discrete time delays in the states of neurons and discrete neutral delays in the time derivatives of the states of neurons. By constructing a novel suitable Lyapunov functional, an easily verifiable algebraic condition for global asymptotic stability of this type of Hopfield neural systems is presented. This stability condition is absolutely independent of the discrete time and neutral delays. An instructive example is given to demonstrate the applicability of the proposed condition.

Keywords

Neutral Systems, Hopfield Neural Networks, Lyapunov Functionals, Stability Analysis

Ayrık Gecikmeli Nötral-Tip Hopfield Yapay Sinir Ağlarının Bir Kararlılık Analizi

Abstract

Bu araştırma makalesi, nöron durumlarının ayrık zaman gecikmeleri ve nöron durumlarının türevlerinin ayrık nötral gecikmeler içerdiği nötral-tip Hopfiled yapay sinir ağlarının kararlılık problemi ile ilgilenmektedir. Yeni ve uygun bir Lyapunov fonksiyonu kullanılarak, bu tip Hopfield yapay sinir ağlarının kararlılığı için, yeni ve kolayca doğrulanabilir cebirsel olarak ifade edilen bir koşul sunulmaktadır. Bu kararlılık koşulu kesinlikle hem ayrık zaman gecikmeleri hem de ayrık nötral gecikmelerinden bağımsızdır. Elde edilen kararlılık koşulunun uygulanabilirliğini göstermek için öğretici bir sayısal örnek verilmiştir.

Keywords

Nötral Sistemler, Hopfield Yapay Ağları, Lyapunov Fonksiyonları, Kararlılık Analizi

References

• J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proceedings of National Academy of Science, 79, 2554-2558, (1982).
• J. Wang, Y. Cai and J. Yin, Multi-start stochastic competitive Hopfield neural network for frequency assignment problem in satellite communications, Expert Systems with Applications, 38, 131-145, 10.1016/j.eswa.2010.06.027 (2011).
• S. C. Tong, Y. M. Li and H. G. Zhang, Adaptive neural network decentralized backstepping output-feedback control for nonlinear large-scale systems with time delays, IEEE Transactions on Neural Networks, 22, 1073-1086, 10.1109/TNN.2011.2146274, (2011).
• M. Galicki, H. Witte, J. Dorschel, M. Eiselt and G. Griessbach, Common optimization of adaptive preprocessing units and a neural network during the learning period. Application in EEG pattern recognition, Neural Networks, 10, 1153-1163, 10.1109/TNN.2011.2146274 (1997).
• B. Kosko, Bi-directional associative memories, IEEE Transactins on System, Man and Cybernetics, 18, 49-60, 10.1109/21.87054, 1988.
• H. Zhu, R. Rakkiyappan and X. Li, Delayed state-feedback control for stabilization of neural networks with leakage delay, Neural Networks, 105, 249-255, doi.org/10.1016/j.neunet.2018.05.013 (2018).
• J. Wang, H. Jiang, T. Ma and C. Hu, Delay-dependent dynamical analysis of complex-valued memristive neural networks: Continuous time and discrete-time cases, Neural Networks, 101, 33-46, 10.1016/j.neunet.2018.01.015, (2018).
• Q. Zhu and J. Cao, Robust exponential stability of Markovian jump impulsive stochastic Cohen-Grossberg neural networks with mixed time delays, IEEE Transactions on Neural Networks, 21, 1314-1325, 10.1109/TNN.2010.2054108, (2010).
• X. Huang, J. Jia, Y. Fan, Z. Wang and J. Xia, Interval matrix method based synchronization criteria for fractional-order memristive neural networks with multiple time-varying delays, Journal of the Franklin Institute, 357, 1707-1733, 10.1016/j.jfranklin.2019.12.014, (2020).
• S. Arik, New Criteria for Global Robust Stability of Delayed Neural Networks With Norm-Bounded Uncertainties, IEEE Transactions on Neural Networks and Learning Systems, vol. 25, 1045-1052, 10.1109/TNNLS.2013.2287279, (2014).
• C. Ge, C. Hua and X. Guan, New Delay-Dependent Stability Criteria for Neural Networks With Time-Varying Delay Using Delay-Decomposition Approach, IEEE Transactions on Neural Networks and Learning Systems, 25, 1378-1383, 10.1109/TNNLS.2013.2285564, (2014).
• R. Manivannan, R.Samidurai, J. Cao, A. Alsaedi and F. E.Alsaadi, Global exponential stability and dissipativity of generalized neural networks with time-varying delay signals, Neural Networks, 87, 149-159, doi.org/10.1016/j.neunet.2016.12.005 (2017).
• S. I. Niculescu, Delay Effects on Stability: A Robust Control Approach, Springer, Berlin, 2001.
• V. B. Kolmanovskii and V. R. Nosov, Stability of Functional Differential Equations, Academic Press, London, 1986.
• Y. Kuang, Delay Differential Equations with Applications in Population Dynamics, Academic Press, Boston, 1993.
• M S. Mahmoud and A. Ismail, Improved results on robust exponential stability criteria for neutral-type delayed neural networks, Applied Mathematics and Computation, 217, 3011-3019, doi.org/10.1016/j.amc.2010.08.034, (2010).
• J. H. Park, O.M. Kwon and S.M. Lee, LMI optimization approach on stability for delayed neural networks of neutral-type, Applied Mathematics and Computation, 196, 236–244, 10.1016/j.amc.2007.05.047, (2008).
• R. Rakkiyappan, P. Balasubramaniam, LMI conditions for global asymptotic stability results for neutral-type neural networks with distributed time delays, Applied Mathematics and Computation, 204, 317-324, doi.org/10.1016/j.amc.2008.06.049, (2008).
• S.M. Lee, O.M. Kwon and J. H. Park, A novel delay-dependent criterion for delayed neural networks of neutral type, Physics Letters A, 374, 1843–1848, 10.1016/j.physleta.2010.02.043, (2010).
• S. Xu, J. Lam, W. C. Ho and Y. Zou, Delay-dependent exponential stability for a class of neural networks with time delays, Journal of Computational and Applied Mathematics, 183, 16–28, doi.org/10.1016/j.cam.2004.12.025 (2005).
• R. Rakkiyappan and P. Balasubramaniam, New global exponential stability results for neutral type neural networks with distributed time delay, Neurocomputing, 71, 1039–1045, 10.1016/j.neucom.2007.11.002, (2008).
• Z. Orman, New sufficient conditions for global stability of neutral-type neural networks with time delays, Neurocomputing, 97, 141-148, doi.org/10.1016/j.neucom.2012.05.016, (2012)
• W. Weera and P. Niamsup, Novel delay-dependent exponential stability criteria for neutral-type neural networks with non-differentiable time-varying discrete and neutral delays, Neurocomputing, 173, 886-898, doi.org/10.1016/j.neucom.2015.08.044, (2016).
• M. Zheng, L. Li, H. Peng, J. Xiao, Y. Yang and H. Zhao, Finite-time stability analysis for neutral-type neural networks with hybrid time-varying delays without using Lyapunov method, Neurocomputing, 238, 67-75, doi.org/10.1016/j.neucom.2017.01.037, (2017).
• Y. Dong, L. Guo and J. Hao, Robust exponential stabilization for uncertain neutral neural networks with interval time-varying delays by periodically intermittent control, Neural Computing and Applications, 32, 2651–2664, 10.1007/s00521-018-3671-2, (2020).
• K. Shi, H. Zhu, S. Zhong, Y. Zeng and Y. Zhang, New stability analysis for neutral type neural networks with discrete and distributed delays using a multiple integral approach, Journal of the Franklin Institute, 352, 155-176, doi.org/10.1016/j.jfranklin.2014.10.005, (2015).
• K. Shi, S. Zhong, H. Zhu, X. Liu and Y. Zen, New delay-dependent stability criteria for neutral-type neural networks with mixed random time-varying delays, Neurocomputing, 168, 896-907, 10.1016/j.neucom.2015.05.035, (2015).
• D. Liu and Y. Du, New results of stability analysis for a class of neutral-type neural network with mixed time delays, International Journal of Machine Learning and Cybernetics, 6, 555–566, doi.org/10.1007/s13042-014-0302-9, (2015).
• R. Samidurai, S. Rajavel, R. Sriraman, J. Cao, A. Alsaedi, and F. E. Alsaadi, Novel results on stability analysis of neutral-type neural networks with additive time-varying delay components and leakage delay, International Journal of Control, Automation and Systems, 15, 1888-1900, 10.1007/s12555-016-9483-1, (2017).
• K. Shi H. Zhu, S. Zhong, Y. Zeng, Y. Zhang and W. Wang, Stability analysis of neutral type neural networks with mixed time varying delays using triple-integral and delay-partitioning methods, ISA Transactions, 58, 85-95, doi.org/10.1016/j.isatra.2015.03.006, (2015).
• Balasubramaniam, G. Nagamani and R. Rakkiyappan, Global passivity analysis of interval neural networks with discrete and distributed delays of neutral type, Neural Processing Letters, 32, 109–130, doi.org/10.1007/s11063-010-9147-8, (2010).
• H. Mai, X. Liao and C. Li, A semi-free weighting matrices approach for neutral-type delayed neural networks, Journal of Computational and Applied Mathematics, 225, 44-55, doi.org/10.1016/j.cam.2008.06.016, (2009).
• S. Lakshmanan, C.P. Lim, M. Prakash, S. Nahavandi and P. Balasubramaniam, Neutral-type of delayed inertial neural networks and their stability analysis using the LMI Approach, Neurocomputing, 230, 243-250, 10.1016/j.neucom.2016.12.020, (2017).
• J. Zhu, Q. Zhang and C. Yang, Delay-dependent robust stability fo rHopfield neural networks of neutral-type, Neurocomputing, 72, 2609–2617, doi.org/10.1016/j.neucom.2008.10.008, (2009).R. Manivannan, R. Samidurai, J. Cao, A. Alsaedi and F. E.
• Alsaadi, Stability analysis of interval time-varying delayed neural networks including neutral time-delay and leakage delay, Chaos, Solitons and Fractals, 114, 433–445, 10.1016/j.chaos.2018.07.041, (2018).
• Z. Tu and L. Wang, Global Lagrange stability for neutral type neural networks with mixed time-varying delays, International Journal of Machine Learning and Cybernetics, 9, 599–60, doi.org/10.1007/s13042-016-0547-6, (2018).
• Y. Ma, N. Ma, L. Chen, Y. Zheng and Y. Han, Exponential stability for the neutral-type singular neural network with time-varying delays, International Journal of Machine Learning and Cybernetics, 10, 853–858, 10.1007/s13042-017-0764-7, (2019).
• C.H. Lien, K.W. Yu, Y. F. Lin, Y. J. Chung, and L. Y. Chung, Global exponential stability for uncertain delayed neural networks of neutral type with mixed time delays, IEEE Transactions on Systems, Man, and Cybernetics—Part B:Cybernetics, 38, 709-720, 10.1109/TSMCB.2008.918564, (2008).