Dissipativity analysis of memristor-based complex-valued neural networks with time-varying delays

In this paper, the problem of dissipativity analysis for memristor-based complex-valued neural networks (MCVNNs) with time-varying delays is investigated extensively. Dissipativity analysis is an important concept in control system theory and its applications. The analysis in the paper employ results from the theory of differential equations with discontinuous right-hand side as introduced by Filippov. By using the framework of Filippov solution, differential inclusion theory, an appropriate Lyapunov-Krasovskii functional and linear matrix inequality (LMI) technique, several new sufficient conditions for global dissipativity, global exponential dissipativity and strictly ( Q , S , R ) -dissipativity are derived in the form of complex-valued as well as real-valued LMIs. Both real and complex-valued LMIs guarantee feasibility results for addressed MCVNNs. These LMIs can be solved by using standard available numerical packages. Moreover, the global attractive sets which are positive invariant are obtained. Finally, three numerical examples are established to illustrate the effectiveness of the proposed theoretical results.

[1]  Jun Wang,et al.  Global Stability of Complex-Valued Recurrent Neural Networks With Time-Delays , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Zhigang Zeng,et al.  Passivity analysis of memristive neural networks with different memductance functions , 2014, Commun. Nonlinear Sci. Numer. Simul..

[3]  André Ricardo Backes,et al.  Texture analysis and classification: A complex network-based approach , 2013, Inf. Sci..

[4]  Zhigang Zeng,et al.  Lagrange stability of neural networks with memristive synapses and multiple delays , 2014, Inf. Sci..

[5]  Y. Pershin,et al.  Spin Memristive Systems: Spin Memory Effects in Semiconductor Spintronics , 2008, 0806.2151.

[6]  B. Brogliato,et al.  Dissipative Systems Analysis and Control , 2000 .

[7]  Guodong Zhang,et al.  New Algebraic Criteria for Synchronization Stability of Chaotic Memristive Neural Networks With Time-Varying Delays , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Zhigang Zeng,et al.  Dynamic behaviors of memristor-based recurrent neural networks with time-varying delays , 2012, Neural Networks.

[9]  J. Willems.  Dissipative dynamical systems part I: General theory , 1972 .

[10]  Zhigang Zeng,et al.  Passivity analysis of memristor-based recurrent neural networks with time-varying delays , 2013, J. Frankl. Inst..

[11]  Tohru Nitta,et al.  Orthogonality of Decision Boundaries in Complex-Valued Neural Networks , 2004, Neural Computation.

[12]  P. Moylan,et al.  Dissipative Dynamical Systems: Basic Input-Output and State Properties , 1980 .

[13]  Lihong Huang,et al.  Periodicity and dissipativity for memristor-based mixed time-varying delayed neural networks via differential inclusions , 2014, Neural Networks.

[14]  J. Yang,et al.  Memristive switching mechanism for metal/oxide/metal nanodevices. , 2008, Nature nanotechnology.

[15]  Yan Sun,et al.  Dissipativity analysis of neural networks with time-varying delays , 2008, Int. J. Autom. Comput..

[16]  Jinde Cao,et al.  Global dissipativity analysis on uncertain neural networks with mixed time-varying delays. , 2008, Chaos.

[17]  Xin Wang,et al.  Global exponential stability of a class of memristive neural networks with time-varying delays , 2013, Neural Computing and Applications.

[18]  Akira Hirose,et al.  Applications of complex-valued neural networks to coherent optical computing using phase-sensitive detection scheme , 1994 .

[19]  Zhigang Zeng,et al.  Global Mittag-Leffler stability and synchronization of memristor-based fractional-order neural networks , 2014, Neural Networks.

[20]  R. Leine,et al.  Bifurcations in Nonlinear Discontinuous Systems , 2000 .

[21]  Jinde Cao,et al.  Dissipativity and quasi-synchronization for neural networks with discontinuous activations and parameter mismatches , 2011, Neural Networks.

[22]  Xiaohui Xu,et al.  Exponential stability of complex-valued neural networks with mixed delays , 2014, Neurocomputing.

[23]  Zhaoning Yu,et al.  Nonlinear optical spectroscopy of photonic metamaterials , 2007, 2008 Conference on Lasers and Electro-Optics and 2008 Conference on Quantum Electronics and Laser Science.

[24]  Jinde Cao,et al.  Global robust stability of delayed recurrent neural networks , 2004 .

[25]  Jing Wang,et al.  Delay-dependent robust dissipativity conditions for delayed neural networks with random uncertainties , 2013, Appl. Math. Comput..

[26]  Q. Song,et al.  Boundedness and Stability for Discrete-Time Delayed Neural Network with Complex-Valued Linear Threshold Neurons , 2010 .

[27]  Zhigang Zeng,et al.  On the periodic dynamics of memristor-based neural networks with time-varying delays , 2014, Inf. Sci..

[28]  S. Arik.  Global robust stability of delayed neural networks , 2003 .

[29]  Qiankun Song,et al.  Global stability of complex-valued neural networks with both leakage time delay and discrete time delay on time scales , 2013, Neurocomputing.

[30]  Xiaomei Zhang,et al.  Dissipative synchronization of nonlinear chaotic systems under information constraints , 2013, Inf. Sci..

[31]  J. Tour,et al.  Electronics: The fourth element , 2008, Nature.

[32]  Pagavathigounder Balasubramaniam,et al.  An LMI approach for global robust dissipativity analysis of T-S fuzzy neural networks with interval time-varying delays , 2012, Expert Syst. Appl..

[33]  Guodong Zhang,et al.  Global exponential stability of a class of memristor-based recurrent neural networks with time-varying delays , 2012, Neurocomputing.

[34]  Aleksej F. Filippov,et al.  Differential Equations with Discontinuous Righthand Sides , 1988, Mathematics and Its Applications.

[35]  Huabin Chen,et al.  Delayed-state-feedback exponential stabilization for uncertain Markovian jump systems with mode-dependent time-varying state delays , 2012 .

[36]  Jun Wang,et al.  Global dissipativity of continuous-time recurrent neural networks with time delay. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[37]  Akira Hirose,et al.  Complex-Valued Neural Networks , 2006, Studies in Computational Intelligence.

[38]  Zhigang Zeng,et al.  Synchronization control of a class of memristor-based recurrent neural networks , 2012, Inf. Sci..

[39]  S. Arik.  On the global dissipativity of dynamical neural networks with time delays , 2004 .

[40]  Jacek M. Zurada,et al.  Discrete-Time Recurrent Neural Networks With Complex-Valued Linear Threshold Neurons , 2009, IEEE Trans. Circuits Syst. II Express Briefs.

[41]  Jun Wang,et al.  Global uniform asymptotic stability of memristor-based recurrent neural networks with time delays , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[42]  Jun Wang,et al.  Global exponential dissipativity and stabilization of memristor-based recurrent neural networks with time-varying delays , 2013, Neural Networks.

[43]  Qiankun Song,et al.  Global -Stability of Complex-Valued Neural Networks with Unbounded Time-Varying Delays , 2014 .

[44]  John H. Mathews,et al.  Complex analysis for mathematics and engineering , 1995 .

[45]  J. Hale.  Asymptotic Behavior of Dissipative Systems , 1988 .

[46]  D. Stewart,et al.  The missing memristor found , 2008, Nature.

[47]  PooGyeon Park,et al.  Reciprocally convex approach to stability of systems with time-varying delays , 2011, Autom..

[48]  Jinde Cao,et al.  Global robust stability of interval cellular neural networks with time-varying delays , 2005 .

[49]  Quan Yin,et al.  Global exponential periodicity and stability of a class of memristor-based recurrent neural networks with multiple delays , 2013, Inf. Sci..

[50]  L. Chua.  Memristor-The missing circuit element , 1971 .

[51]  Bernhard Maschke,et al.  Dissipative Systems Analysis and Control , 2000 .

[52]  Derong Liu,et al.  Data-based stability analysis of a class of nonlinear discrete-time systems , 2013, Inf. Sci..

[53]  Qiankun Song,et al.  Boundedness and Complete Stability of Complex-Valued Neural Networks With Time Delay , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[54]  T Soddemann,et al.  散逸粒子動力学:平衡および非平衡分子動力学シミュレーションのための有用なサーモスタット(原標題は英語) , 2003 .