Robust stability analysis of competitive neural networks with different time-scales under perturbations

Neurocomputing

Volumn 71, Issue 1-3, 2007, Pages 417-420

  Meyer Base A ^a   Roberts, R ^a   Yu, H G ^a  

^a FAMU FSU COLLEGE OF ENGINEERING   (United States)

Author keywords

Noise perturbation; Robust stability; Singularly perturbed system; Two time scale neural network

Indexed keywords

ASYMPTOTIC STABILITY; LYAPUNOV METHODS; PERTURBATION TECHNIQUES; SYSTEM STABILITY; UNCERTAIN SYSTEMS;

COMPETITIVE NEURAL NETWORKS; NOISE PERTURBATION; SINGULARLY PERTURBED SYSTEM;

NEURAL NETWORKS;

ACCURACY; ARTICLE; ARTIFICIAL NEURAL NETWORK; LONG TERM MEMORY; MATHEMATICAL ANALYSIS; MATHEMATICAL COMPUTING; MATHEMATICAL PARAMETERS; NERVE CONDUCTION; PRIORITY JOURNAL; SHORT TERM MEMORY; SYNAPSE; TIME;

EID: 35648947253     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2007.08.014     Document Type: Article

References (8)

1. Feng Z., and Michel A.N. Robustness analysis of a class of discrete-time recurrent neural networks under perturbations. IEEE Trans. Circuit Syst. I 46 2 (1999) 1482-1486
2. Lu H., and Chen G. Global exponential convergence of multitime scale neural networks. IEEE Trans. Circuit Syst. II 52 10 (2005) 761-765
3. Meyer-Bäse A., Pilyugin S., and Chen Y. Global exponential stability of competitive neural networks with different time scales. IEEE Trans. Neural Networks 2 (2003) 716-719
4. S. Sen, K. Datta, Stability bounds of singularly perturbed systems, IEEE Trans. Autom. Control (June 1993) 302-304.
5. Z. Shao, Robust stability of two-time scale systems with nonlinear uncertainties, IEEE Trans. Autom. Control (June 2004) 258-261.
6. A. Saberi, H. Khalil, Quadratic-type lyapunov functions for singularly perturbed systems, IEEE Trans. Autom. Control (June 1984) 542-550.
7. Vidyasagar M., and Nonlinear Systems Analysis. Prentice-Hall (1993), Englewod Cliffs, NJ
8. Wang K., and Michel A.N. Robustness and perturbation analysis of a class of nonlinear systems with applications to neural networks. IEEE Trans. Circuit Syst. I 41 2 (1994) 229-243