Global exponential stability via inequality technique for inertial BAM neural networks with time delays

Abstract In this paper, the existence and global exponential stability of equilibrium point for inertial BAM neural networks with time delays are discussed. Firstly, by using homeomorphism theory and inequality technique, the LMI-based sufficient condition on the existence and uniqueness of equilibrium point for above inertial BAM neural networks is obtained. Secondly, a LMI-based condition which can ensure the global exponential stability of equilibrium point for the system is obtained by using LMI method and inequality technique. In our results, the boundedness assumption on the activation functions in Ke and Miao (2013) [19] , [20] is removed. Hence, our result on global exponential stability of equilibrium point for above system is less conservative.

[1]  B Kosko,et al.  Adaptive bidirectional associative memories. , 1987, Applied optics.

[2]  Jinde Cao,et al.  Stability and Hopf Bifurcation in a Simplified BAM Neural Network With Two Time Delays , 2007, IEEE Transactions on Neural Networks.

[3]  Zhengqiu Zhang,et al.  New LMI-based condition on global asymptotic stability concerning BAM neural networks of neutral type , 2012, Neurocomputing.

[4]  Jun Tani.  Proposal of chaotic steepest descent method for neural networks and analysis of their dynamics , 1992 .

[5]  X. Liao,et al.  Dynamics of an inertial two-neuron system with time delay , 2009 .

[6]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[7]  X. Liao,et al.  Hopf bifurcation and chaos in a single inertial neuron model with time delay , 2004, nlin/0411027.

[8]  Jinde Cao,et al.  Dynamics of bidirectional associative memory networks with distributed delays and reaction–diffusion terms , 2007 .

[9]  X. Liao,et al.  Stability of bifurcating periodic solutions for a single delayed inertial neuron model under periodic excitation , 2009 .

[10]  R. Westervelt,et al.  Dynamics of simple electronic neural networks , 1987 .

[11]  Guoyin Wang,et al.  Research for Hopf bifurcation of an inertial two-neuron system with time delay , 2006, 2006 IEEE International Conference on Granular Computing.

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

[13]  Xiaofeng Liao,et al.  The Research for Hopf Bifurcation in a Single Inertial Neuron Model with External Forcing , 2007 .

[14]  Ke Yunquan,et al.  Stability and existence of periodic solutions in inertial BAM neural networks with time delay , 2013, Neural Computing and Applications.

[15]  Zhengqiu Zhang,et al.  Global exponential stability of interval general BAM neural networks with reaction-diffusion terms and multiple time-varying delays , 2011, Neural Networks.

[16]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[17]  Yunquan Ke,et al.  Stability analysis of inertial Cohen-Grossberg-type neural networks with time delays , 2013, Neurocomputing.

[18]  X. Lou,et al.  Global asymptotic stability of BAM neural networks with distributed delays and reaction–diffusion terms , 2006 .

[19]  Q. Song,et al.  Global exponential stability of BAM neural networks with distributed delays and reaction–diffusion terms , 2005 .

[20]  Jun Tani,et al.  Model-based learning for mobile robot navigation from the dynamical systems perspective , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[21]  Zhengqiu Zhang,et al.  Existence and global exponential stability of a periodic solution to interval general bidirectional associative memory (BAM) neural networks with multiple delays on time scales , 2011, Neural Networks.