Some New Stability Properties of Dynamic Neural Networks with Different Time-scales

Dynamic neural networks with different time-scales include the aspects of fast and slow phenomenons. Some applications require that the equilibrium points of these networks to be stable. The main contribution of the paper is that Lyapunov function and singularly perturbed technique are combined to access several new stable properties of different time-scales neural networks. Exponential stability and asymptotic stability are obtained by sector and bound conditions. Compared to other papers, these conditions are simpler. Numerical examples are given to demonstrate the effectiveness of the theoretical results.

[1]  GrossbergS..  Adaptive pattern classification and universal recoding , 1976 .

[2]  S. Grossberg,et al.  Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors , 1976, Biological Cybernetics.

[3]  Frank L. Lewis,et al.  Identification of nonlinear dynamical systems using multilayered neural networks , 1996, Autom..

[4]  Manolis A. Christodoulou,et al.  Adaptive control of unknown plants using dynamical neural networks , 1994, IEEE Trans. Syst. Man Cybern..

[5]  Mao Ye,et al.  Complete Convergence of Competitive Neural Networks with Different Time Scales , 2005, Neural Processing Letters.

[6]  Bruno A. Olshausen,et al.  A Nonlinear Hebbian Network that Learns to Detect Disparity in Random-Dot Stereograms , 1996, Neural Computation.

[7]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Xiaoou Li,et al.  Some stability properties of dynamic neural networks , 2001 .

[9]  Eduardo Sontag,et al.  On characterizations of the input-to-state stability property , 1995 .

[10]  Johan A. K. Suykens,et al.  Robust local stability of multilayer recurrent neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[11]  Anke Meyer-Bäse,et al.  Singular Perturbation Analysis of Competitive Neural Networks with Different Time Scales , 1996, Neural Computation.

[12]  Shun-ichi Amari,et al.  Competitive and Cooperative Aspects in Dynamics of Neural Excitation and Self-Organization , 1982 .

[13]  A. Isidori,et al.  Passivity, feedback equivalence, and the global stabilization of minimum phase nonlinear systems , 1991 .

[14]  Anke Meyer-Bäse,et al.  Global exponential stability of competitive neural networks with different time scales , 2003, IEEE Trans. Neural Networks.

[15]  B. V. K. Vijaya Kumar,et al.  Emulating the dynamics for a class of laterally inhibited neural networks , 1989, Neural Networks.

[16]  M. Forti,et al.  Necessary and sufficient condition for absolute stability of neural networks , 1994 .

[17]  Marios M. Polycarpou,et al.  High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[18]  Wen Yu,et al.  Passivity analysis for dynamic multilayer neuro identifier , 2003 .

[19]  Kiyotoshi Matsuoka,et al.  Stability conditions for nonlinear continuous neural networks with asymmetric connection weights , 1992, Neural Networks.

[20]  Fuchun Sun,et al.  Stability analysis and synthesis of fuzzy singularly perturbed systems , 2005, IEEE Trans. Fuzzy Syst..

[21]  E. Kaszkurewicz,et al.  On a class of globally stable neural circuits , 1994 .

[22]  Anthony J. Calise,et al.  Adaptive output feedback control of uncertain nonlinear systems using single-hidden-layer neural networks , 2002, IEEE Trans. Neural Networks.

[23]  Hongtao Lu,et al.  Global exponential stability of delayed competitive neural networks with different time scales , 2005, Neural Networks.

[24]  Liang Jin,et al.  Stable dynamic backpropagation learning in recurrent neural networks , 1999, IEEE Trans. Neural Networks.