Abstract
By constructing novel Lyapunov functionals and using some new complex-valued inequalities, a new LMI-based sufficient condition on global asymptotic stability of equilibrium point for complex-valued recurrent neural networks with time-varying delays is established. In our result, the assumption for boundedness in existing papers on the complex-valued activation functions is removed and the matrix inequalities used in recent papers are replaced with new matrix inequalities. On the other hand, we construct new Lyapunov functionals which are different from those constructed in existing papers. Hence, our result is less conservative, new and complementary to the previous results.
Similar content being viewed by others
References
Hu J, Wang J (2012) Global stability of complex-valued recurrent neural networks with time-delays. IEEE Trans Neural Netw Learn Syst 23(6):853–865
Bohner M, Rao VSH, Sanyal S (2011) Global stability of complex-valued neural networks on time scales. Differ Equ Dyn Syst 19(1–2):3–11
Zhang ZY, Lin C (2014) Global stability criterion for delayed complex-valued recurrent neural networks. IEEE Trans Neural Netw Learn Syst 25(9):1704–1708
Fang T, Sun JT (2014) Further investigate the stability of complex-valued recurrent neural networks with time-delays, IEEE Trans Neural Netw Learn Syst 25(9):1709–1713
Hirose A (2010) Recent progress in applications of complex-valued neural networks. In: Proceedings of 10th international conference on artificial intelligence and soft computing, pp 42–46
Liu X, Fang K, Liu B (2009) A synthesis method based on stability analysis for complex-valued Hopfield neural networks. In: Proceedings on 7th Asian control conference, pp 1245–1250
Hirose A (2003) Complex-valued neural networks: theories and applications, vol 5. World Scientific, Singapore
Zhou W, Zurada J (2009) Discrete-time recurrent neural networks with complex-valued linear threshold neurons. IEEE Trans Circuits Syst II Exp Brief 56(8):669–673
Duan C, Song Q (2010) Boundedness and stability for discrete-time delayed neural network with complex-valued linear threshold neurons. Discrete Dyn Nat Soc 2010:1–19
Ozdemir N, Iskender B, Ozgur N (2011) Complex-valued neural network with Mobius activation function. Commun Nonlinear Sci Numer Simul 16(12):4698–4703
Hashimoto N, Kuroe Y, Mori T (1999) An energy function for complex-valued neural networks and its applications. In: Proceedings of Annual conference of the institute of System, Control and Information Engineers, vol 43, pp. 391–392
Kuroe Y, Yoshid M, Mori T (2003) On activation functions for complex-valued neural networks: existence of energy functions. In: Proceedings of ICANN/ICONIP, pp 174–175
Liu X, Chen T (2016) Global exponential stability for complex-valued recurrent neural networks with asynchronous time delays. IEEE Trans Neural Netw Learn Syst (to appear)
Gong W, Liang J, Cao J (2015) Complex-valued recurrent neural networks with time-varying delays. Neural Netw 70:81–89
Velmurugan G, Rakkiyappan R, Cao J (2015) Further analysis of global \(\mu \)-stability of complex-valued neural networks with unbounded time-varying delays. Neural Netw 67:14–27
Pan J, Liu XZ, Xie WC (2015) Exponential stability of a class of complex-valued neural networks with time-varying delays. Neurocomputing 164:293–299
Song QK, Zhao ZJ, Liu YR (2015) Stability analysis of complex-valued neural networks with probabilistic time-varying delays. Neurocomputing 159(2):96–104
Zhang ZQ, Yu SH (2016) Global asymptotic stability of a class of complex-valued Cohen–Grossberg neural networks with time delays. Neurocomputing 171:1158–1166
Zhang ZQ, Hao DL, Zhou DM (2017) Global asymptotic stability by complex-valued inequalities for complex-valued neural networks with delays on periodic time scales. Neurocomputing 219:494–501
Wang ZY, Huang LH (2016) Global stability analysis for complex-valued BAM neural networks. Neurocomputing 73:2083–2089
Song QK, Zhao ZJ (2016) Stability criterion of complex-valued neural networks with both leakage delay and time-barying on time scales. Neurocomputing 171:179–184
Chen XF, Song QK (2013) Global stability of complex-valued neural networks with both leakage time delay and discrete time delay on time scales. Neurocomputing 121:254–264
Velmurugan G, Rakkiyappan R, Lakshmanan S (2015) Passivity analysis of memristor-based complex-valued neural networks with time-varying delays. Neural Process Lett 42:517–540
Yu SH, Zhang ZQ (2015) New global exponential stability conditions for inertial Cohen-Grossberg neural networks with time delays. Neurocomputing 151:1446–1454
Zhang ZQ, Quan ZY (2015) Global exponential stability via inequality technique for inertial BAM neural networks with time delays. Neurocomputing 151:1316–1326
Zheng CD, Gu Y, Liang WL, Wang ZS (2015) Novel delay-dependent stability criteria for switched Hopfield neural networks of neutral type. Neurocomputing 158:117–126
Tan MC (2016) Stabilization of coupled time-delay neural networks with nodes of defferent dimensions. Neural Process Lett 43:255–268
Zhao ZJ, Song QK, He SR (2014) Passivity analysis of stochastic neural networks with time-varying delays and leakage delay. Neurocomputing 125:22–27
Zhao B, Song QK, Wang HW (2011) Global exponential stability of neural networks with discrete and distributed delays and general activation functions on time scales. Neurocomputing 74:3142–3150
Park P, Lee W, Lee SY (2015) Auxiliary function-based integral inequalities for quadratic functions and their applications to time-delay system. J Franklin Inst 352:1378–1396
Zhu QX, Cao JD, Rakkiyapan R (2015) Exponential input-to-state stability of stochastic Cohen–Grossberg neural networks with mixed delays. Nonlinear Dyn 79(2):1085–1098
Zeng HB, He Y, Wu M, She JH (2015) New results on stability analysis for systems with discrete distributed delay. Automatica 60:189–192
Zhu QX, Cao JD (2012) Stability analysis of Markovian Jump stochastic BAM neural networks with impulse control and mixed time delays. IEEE Trans Neural Netw Learn Syst 23(3):467–479
Zeng HB, He Y, Wu M, She JH (2015) Free-matrix-based integral inequality for stability analysis of system with time-varying delay. IEEE Trans Autom Control 60(10):2768–2772
Zhu QX, Rakkiyappan R, Chandrasekar A (2014) Stochastic stability of Markovian jump BAM neural networks with leakage delays and impulse control. Neurocomputing 136:136–151
Zhu QX, Cao JD (2012) Stability of Markovian jump neural networks with impulse control and time varying delays. Nonlinear Anal Real World Appl 13(5):2259–2270
Li CJ, Yu XH, Huang TW, Chen G, He X (2016) A generalized Hopfield network for nonsmooth constrained convex optimization: Lie derivative approach. IEEE Trans Neural Netw Learn Syst 27(2):308–321
He X, Huang TW, Yu JZ, Li CD, Li CJ (2017) An inertial projection neural networks for solving variational inequalitits. IEEE Trans Cybern 47(3):809–814
Acknowledgements
Funding was provided by Education Department of Hunan Province (Grant No. 201485).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, Z., Hao, D. Global Asymptotic Stability for Complex-Valued Neural Networks with Time-Varying Delays via New Lyapunov Functionals and Complex-Valued Inequalities. Neural Process Lett 48, 995–1017 (2018). https://doi.org/10.1007/s11063-017-9757-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-017-9757-5