Relaxed passivity conditions for discrete-time stochastic delayed neural networks

详细信息    查看全文

• 作者：Wei Kang ; Shouming Zhong ; Jun Cheng
• 关键词：Passivity ; Discrete ; time systems ; Stochastic neural networks ; Time ; varying delays
• 刊名：International Journal of Machine Learning and Cybernetics
• 出版年：2016
• 出版时间：April 2016
• 年：2016
• 卷：7
• 期：2
• 页码：205-216
• 全文大小：560 KB
• 参考文献：1.Duan L, Huang L (2014) Periodicity and dissipativity for memristor-based mixed time-varying delayed neural networks via differential inclusions. Neural Netw 57:12–22CrossRef MATH
  2.Park PG, Ko JW, Jeong C (2011) Reciprocally convex approach to stability of systems with time-varying delays. Automatica 47:235–238MathSciNet CrossRef MATH
  3.Chen W, Zheng W (2006) Global asymptotic stability of a class of neural networks with distributed delays. IEEE Trans Circuits Syst I 53:644–652MathSciNet CrossRef
  4.Tsang ECC, Wang X, Yeung DS (2000) Improving learning accuracy of fuzzy decision trees by hybrid neural networks. IEEE Trans Fuzzy Syst 8:601–614CrossRef
  5.Wang X, Dong C, Fan T (2007) Training T-S norm neural networks to refine weights for fuzzy if-then rules. Neurocomputing 70:2581–2587CrossRef
  6.Zhang D, Yu L (2012) Exponential state estimation for Markovian jumping neural networks with time-varying discrete and distributed delays. Neural Netw 35:103–111CrossRef MATH
  7.Shi K, Zhu H, Zhong S, Zeng Y, Zhang Y (2015) New stability analysis for neutral type neural networks with discrete and distributed delays using using a multiple integral approach. J Frankl Inst 352:155–176MathSciNet CrossRef MATH
  8.Cheng J, Xiong L (2015) Improved integral inequality approach on stabilization for continuous-time systems with time-varying input delay. Neurocomputing 160:274–280CrossRef
  9.Liu P (2013) Delay-dependent global exponential robust stability for delayed cellular neural networks with time-varying delay. ISA Trans 52:711–716CrossRef
  10.Liu P (2012) A delay decomposition approach to robust stability analysis of uncertain systems with time-varying delay. ISA Trans 51:694–701CrossRef
  11.Wu Z, Shi P, Su H, Chu J (2012) Stability and disspativity analysis of static neural networks with time delay. IEEE Trans Neural Netw Learn Syst 23:199–210CrossRef
  12.Duan L, Huang L, Guo Z (2014) Stability and almost periodicity for delayed high-order Hopfield neural networks with discontinuous activations. Nonlinear Dyn 77:1469–1484MathSciNet CrossRef MATH
  13.Zhu Q, Cao J (2010) Stability analysis for stochastic neural networks of neutral type with both Markovian jump parameters and mixed time delays. Neurocomputing 73:2671–2680CrossRef
  14.Yang R, Zhang Z, Shi P (2010) Exponential stability on stochastic neural networks with discrete interval and distributed delays. IEEE Trans Neural Netw 21:169–175CrossRef
  15.Xu S, Lam J (2008) A survey of linear matrix inequality techniques in stability analysis of delay systems. Int J Syst Sci 39:1095–1113MathSciNet CrossRef MATH
  16.Chen Y, Xue A, Zhang W, Zhou S (2010) Robust exponential stability conditions for retarded systems with Lipschitz nonlinear stochastic perturbations. Int J Robust Nonlinear 20:2057–2076MathSciNet CrossRef MATH
  17.Kwon O, Park M, Lee S, Park JH, Cha E (2013) Stability for neural networks with time-varying delays via some new approaches. IEEE Trans Neural Netw 24:181–193CrossRef
  18.Zhang H, Liu Z, Huang G, Wang Z (2010) Novel weighting-delay-based stability criteria for recurrent neural networks with time-varying delay. IEEE Trans Neural Netw 21:91–106CrossRef
  19.Zhang H, Wang Z, Liu D (2014) A comprehensive review of stability analysis of continuous-time recurrent neural networks. IEEE Trans Neural Netw 25:1229–1262MathSciNet CrossRef
  20.Cheng J, Zhu H, Ding Y, Zhong S, Zhong Q (2014) Stochastic finite-time boundedness for Markovian jumping neural networks with time-varying delays. Appl Math Comput 242:281–295MathSciNet CrossRef
  21.Wang Z, Wei G, Feng G (2009) Reliabe \(H_\infty \) control for discrete-time piecewise linear systems with infinite distributed delays. Automatica 45:2991–2994MathSciNet CrossRef MATH
  22.Kwon OM, Park MJ, Park JH, Lee SM, Cha EJ (2013) New criteria on delay-dependent stability for discrete-time neural networks with time-varying delays. Neurocomputing 121:185–194CrossRef MATH
  23.Shen B, Ding X, Wang Z (2013) Finite-horizon \(H_\infty \) fault estimation for linear discrete time-varying systems with delayed measurements. Automatica 49:293–296MathSciNet CrossRef MATH
  24.Zhang Z, Zhang Z, Zhang H, Karimi HR (2014) Finite-time stability analysis and stabilization for linear discrete-time system with time-varying delay. J Frankl Inst 351:3457–3476MathSciNet CrossRef MATH
  25.Mathiyalagan K, Sakthivel R, MarshalAnthoni S (2012) Exponential stability result for discrete-time stochastic fuzzy uncertain neural networks. Phys Lett A 376:901–912CrossRef MATH
  26.Kan X, Shu H, Li Z (2014) Robust state estimation for discrete-time neural networks with mixed time-delays, linear fractional uncertainties and successive packet dropouts. Neurocomputing 135:130–138CrossRef
  27.Wang T, Zhang C, Fei S, Li T (2014) Further stability criteria on discrete-time delayed neural networks with distributed delay. Neurocomputing 111:195–203CrossRef
  28.Hien LV, An NT, Trinh H (2014) New results on state bounding for discrete-time systems with interval time-varying delay and bounded disturbance inputs. IET Control Theory Appl 8:1405–1414MathSciNet CrossRef
  29.Lozana R, Brogliato B, Egeland O, Maschke B (2007) Dissipative systems analysis and control: theory and applications, 2nd edn. Springer, LondonMATH
  30.Zhang B, Xu S, Lam J (2014) Relaxd passivity conditions for neural networks with time-varting delays. Neurocomputing 142:299–306CrossRef
  31.Ji DH, Koo JH, Won SC, Lee SM, Park JH (2011) Passivity-based control for Hopfield neural networks using convex representation. Appl Math Comput 217:6168–6175MathSciNet CrossRef MATH
  32.Wu Z, Park JH, Su H, Chu J (2012) New results on exponential passivity of neural networks with time-delays. Nonlinear Anal Real World Appl 13:1593–1599MathSciNet CrossRef MATH
  33.Lee TH, Park MJ, Park JH, Kwon OM, Lee SM (2014) Extended dissipative analysis for neural networks with time-varying delays. IEEE Trans Neural Netw Learn Syst 25:1936–1941CrossRef
  34.Zeng H, He Y, Min Wu, Xiao H (2014) Improved conditions for passivity of neural networks with a time-varying delay. IEEE Trans Cybernetics 44:785–792CrossRef
  35.Zhao Z, Song Q, He S (2014) Passivity analysis of stochastic neural networks with time-varying delays and leakage delay. Neurocomputing 125:22–27CrossRef
  36.Wu Z, Shi P, Su H, Chu J (2013) Dissipativity analysis for discrete-time stochastic neural networks with time-varying delays. IEEE Trans Neural Netw Learn Syst 24:345–355CrossRef
  37.Song Q, Liang J, Wang Z (2009) Passivity analysis of discrete-time stochastic neural networks with time-varying delays. Neurocomputing 72:1782–1788CrossRef
  38.Raja R, Raja UK, Samidurai R, Leelamani A (2014) Passivity analysis for uncertain discrete-time stochastic BAM neural networks with time-varying delays. Neural Comput Appl 25:756–766MATH
  39.Shi G, Ma Q, Qu Y (2013) Robust passivity analysis of a class of discrete-time stochastic neural networks. Neural Comput Appl 22:1509–1517CrossRef
  
• 作者单位：Wei Kang (1) (2)
  Shouming Zhong (1)
  Jun Cheng (3)
  
  1. School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu, 611731, People’s Republic of China
  2. School of Information Engineering, Fuyang Normal College, Fuyang, 236041, People’s Republic of China
  3. School of Science, Hubei University for Nationalities, Enshi, 44500, People’s Republic of China
  
• 刊物类别：Engineering
• 刊物主题：Artificial Intelligence and Robotics
  Statistical Physics, Dynamical Systems and Complexity
  Computational Intelligence
  Control , Robotics, Mechatronics
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1868-808X

文摘

In this paper, the passivity problem is researched for discrete-time stochastic neural networks with time-varying delay. By utilizing a novel Lyapunov–Krasovskii functional, delay-decomposition method and reciprocally convex approach, some sufficient delay-dependent passivity conditions are established in the form of linear matrix inequalities. Furthermore, these new criteria do not require all the symmetric matrices involved in the employed Lyapunov–Krasovskii functional to be positive definite. Finally, three numerical examples are given to illustrate the reduced conservatism and effectiveness of the proposed method.