Abstract
In this paper, the exponential passivity for bidirectional associative memory (BAM) neural networks with time-varying delays is considered. In our study, the lower and upper bounds of the activation functions are allowed to be either positive, negative or zero. By constructing new and improved Lyapunov–Krasovskii functional and introducing free-weighting matrices, a new and improved delay-dependent exponential passivity criterion for BAM neural networks with time-varying delays is derived in the form of linear matrix inequality (LMI). A numerical example is given to show that the derived condition is less conservative than some existing results given in the literature.
Similar content being viewed by others
References
Boyd S, El Ghaoui L, Feron E, Balakrishnan V (1994) Linear matrix inequalities in system and control theory, vol. 15 of SIAM studies in applied mathematics. SIAM, Philadephia
Cao J, Xiao M (2007) Stability and Hopf bifurcation in a simplified BAM neural network with two time delays. IEEE Trans Neural Netw 18(2):416–430
Ding K, Huang N-J, Xu X (2007) Global robust exponential stability of interval BAM neural networks with mixed delays under uncertainty. Neural Proc Lett 25:127–141
Du Y, Zhong S, Zhou N, Nie L, Wang W (2013) Exponential passivity of BAM neural networks with time-varying delays. Appl Math Comput 221:727–740
Han QL (2005) Absolute stability of time-delay systems with sector-bounded nonlinearity. Autom J IFAC 41:2171–2176
Hu L, Liu H, Zhao Y (2009) New stability criteria for BAM neural networks with time-varying delays. Neurocomputing 72:3245–3252
Kharitonov VL (2013) Time-delay systems: Lyapunov functionals and matrices. Birkhauser, Dordrecht
Kosko B (1992) Neural networks and fuzzy systems a dynamical system approach to machine intelligence. Prentice-Hall, Englewood Cliffs
Kosko B (1987) Adaptive bidirectional associative memories. Appl Opt 26:4947–4960
Kosko B (1988) Bidirectional associative memories. IEEE Trans Syst Man Cybernet 18:49–60
Kwon OM, Lee SM, Park JH, Cha EJ (2012) New approaches on stability criteria for neural networks with time varying delays. Appl Math Comput 218:9953–9964
Kwon OM, Lee SM, Park JH (2012) On improved passivity criteria of uncertain neural networks with time-varying delays. Nonlinear Dyn 67:1261–1271
Liao X, Yu J, Chen G (2002) Novel stability criteria for bidirectional associative memory neural networks with time delays. Int J Circ Theory Appl 30:519–546
Mahmoud MS, Xia Y (2010) LMI-based exponential stability criterion for bidirectional associative memory neural networks. Neurocomputing 74:284–290
Mathiyalagan K, Sakthivel R, Anthoni SM (2012) New robust passivity criteria for stochastic fuzzy BAM neural networks with time-varying delays. Commun Nonlinear Sci Numer Simul 17:1392–1407
Peng S (2010) Global attractive periodic solutions of BAM neural networks with continuously distributed delays in the leakage terms. Nonlinear Anal Real World Appl 11:2141–2151
Phat VN, Trinh H (2013) Design of \(H_{\infty }\) control of neural networks with time-varying delays. Neural Comput Appl 23:323–331
Raja R, Karthik Raja U, Samidurai R, Leelamani A (2014) Passivity analysis for uncertain discrete-time stochastic BAM neural networks with time-varying delays. Neural Comput Appl 25:751–766
Rao VSH, Phaneendra BRM (1999) Global dynamics of bidirectional associative memory neural networks involving transmission delays and dead zone. Neural Netw 12(3):455–465
Sakthivel R, Arunkumar A, Mathiyalagan K, Marshal S (2011) Anthoni, Robust passivity analysis of fuzzy Cohen Grossberg BAM neural networks with time-varying delays. Appl Math Comput 218:3799–3809
Samidurai R, Sakthivel R, Anthoni SM (2009) Global asymptotic stability of BAM neural networks with mixed delays and impulses. Appl Math Comput 212:113–119
Singh YP, Yadav VS, Gupta A, Khare A (2005–2009) Bidirection associative memory neural networks method in the character recognition. J Theor Appl Inf Tech 5:382–386
Thipcha J, Niamsup P (2013) Global exponential stability criteria for bidirectional associative memory neural networks with time-varying delays. Abstr Appl Anal 2013:1–13
Thuan MV, Phat VN (2012) New criteria for stability and stabilization of neural networks with mixed interval time-varying delays. Vietnam J Math 40:79–93
Tu Z, Wanga L, Zha Z, Jian J (2013) Global dissipativity of a class of BAM neural networks with time-varying and unbound delays. Commun Nonlinear Sci Numer Simul 18:2562–2570
Wang B, Jian J, Guo C (2008) Global exponential stability of a class of BAM networks with time-varying delays and continuously distributed delays. Neurocomputing 71:495–501
Wang H, Song Q, Duan C (2010) LMI criteria on exponential stability of BAM neural networks with both time-varying delays and general activation functions. Math Comput Simul 81:837–850
Zeng H-B, He Y, Wua M, Xiao S-P (2011) Passivity analysis for neural networks with a time-varying delay. Neurocomputing 74:730–734
Zhang D, Yu L (2012) Passivity analysis for discrete-time switched neural networks with various activation functions and mixed time delay. Nonlinear Dyn 67:403–411
Zhang XM, Han QL (2009) New Lyapunov–Krasovskii functionals for global asymptotic stability of delayed neural networks. IEEE Trans Neural Netw 20:533–539
Zhang XM, Han QL (2011) Global asymptotic stability for a class of generalized neural networks with interval time-varying delays. IEEE Trans Neural Netw 22:1180–1192
Zhang XM, Han QL (2013) Novel delay-derivative-dependent stability criteria using new bounding techniques. Int J Robust Nonlinear Control 23:1419–1432
Zhang XM, Han QL (2014) Global asymptotic stability analysis for delayed neural networks using a matrix-based quadratic convex approach. Neural Newtw 54:57–69
Zhang Z, Liu K, Yang Y (2012) New LMI-based condition on global asymptotic stability concerning BAM neural networks of neutral type. Neurocomputing 81:24–32
Zhao Z, Liu F, Xie X, Liu X, Tang Z (2013) Asymptotic stability of bidirectional associative memory neural networks with time-varying delays via delta operator approach. Neurocomputing 117:40–46
Zhu S, Shena Y, Chen G (2010) Exponential passivity of neural networks with time-varying delay and uncertainty. Phys Lett A 375:136–142
Acknowledgements
The first author is supported by student scholarship from the Human Resources Development in Science Project (Science Achievement Scholarship of Thailand (SAST)). The second author is supported by Chiang Mai University, Chiang Mai, Thailand.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Thipcha, J., Niamsup, P. New exponential passivity of BAM neural networks with time-varying delays. Neural Comput & Applic 29, 1593–1600 (2018). https://doi.org/10.1007/s00521-016-2657-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2657-1