On global exponential stability of positive neural networks with time-varying delay

This paper presents a new result on the existence, uniqueness and global exponential stability of a positive equilibrium of positive neural networks in the presence of bounded time-varying delay. Based on some novel comparison techniques, a testable condition is derived to ensure that all the state trajectories of the system converge exponentially to a unique positive equilibrium. The effectiveness of the obtained results is illustrated by a numerical example.

[1]  Hal L. Smith,et al.  Monotone Dynamical Systems: An Introduction To The Theory Of Competitive And Cooperative Systems (Mathematical Surveys And Monographs) By Hal L. Smith , 1995 .

[2]  Mohamed Chaabane,et al.  Static State-Feedback Controller and Observer Design for Interval Positive Systems With Time Delay , 2015, IEEE Transactions on Circuits and Systems II: Express Briefs.

[3]  Sabri Arik,et al.  An improved robust stability result for uncertain neural networks with multiple time delays , 2014, Neural Networks.

[4]  A. Tesi,et al.  New conditions for global stability of neural networks with application to linear and quadratic programming problems , 1995 .

[5]  Huaguang Zhang,et al.  A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[6]  Long Wang,et al.  Stability Analysis for Continuous-Time Positive Systems With Time-Varying Delays , 2010, IEEE Transactions on Automatic Control.

[7]  Yong He,et al.  Global exponential stability of neural networks with time-varying delay based on free-matrix-based integral inequality , 2016, Neural Networks.

[8]  Hui Li,et al.  Anti-periodic solutions for high-order Hopfield neural networks with impulses , 2014, Neurocomputing.

[9]  Corentin Briat,et al.  Robust stability and stabilization of uncertain linear positive systems via integral linear constraints: L1‐gain and L∞‐gain characterization , 2012, ArXiv.

[10]  Shuo Wu,et al.  Neural Networks Control of the Ni-MH Power Battery Positive Mill Thickness , 2013 .

[11]  Maoguo Gong,et al.  Change Detection in Synthetic Aperture Radar Images Based on Deep Neural Networks , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[12]  O. Arino,et al.  Delay Differential Equations and Applications , 2006 .

[13]  Jakub Mozaryn,et al.  Design of a Neural Network for an Identification of a Robot Model with a Positive Definite Inertia Matrix , 2010, ICAISC.

[14]  Tianping Chen,et al.  Rn+-global stability of a Cohen-Grossberg neural network system with nonnegative equilibria , 2007, Neural Networks.

[15]  Hamid Reza Feyzmahdavian,et al.  Exponential Stability of Homogeneous Positive Systems of Degree One With Time-Varying Delays , 2013, IEEE Transactions on Automatic Control.

[16]  Tingwen Huang,et al.  Guaranteed $H_{\infty}$ Performance State Estimation of Delayed Static Neural Networks , 2015, IEEE Transactions on Circuits and Systems II: Express Briefs.

[17]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[18]  Bingwen Liu,et al.  Positive almost periodic solutions for recurrent neural networks , 2008 .

[19]  Oliver Mason,et al.  Observations on the stability properties of cooperative systems , 2009, Syst. Control. Lett..

[20]  Hongtao Lu.  Chaotic attractors in delayed neural networks , 2002 .

[21]  Hieu Minh Trinh,et al.  Existence and global asymptotic stability of positive periodic solution of delayed Cohen-Grossberg neural networks , 2014, Appl. Math. Comput..

[22]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[23]  Emil Raschman,et al.  New Digital Architecture of CNN for Pattern Recognition , 2009, 2009 MIXDES-16th International Conference Mixed Design of Integrated Circuits & Systems.

[24]  T. T. Loan,et al.  Exponential Stability of Non-Autonomous Neural Networks with Heterogeneous Time-Varying Delays and Destabilizing Impulses , 2016, Vietnam Journal of Mathematics.