DocumentCode :
791748
Title :
Robust Stability and Robust Periodicity of Delayed Recurrent Neural Networks With Noise Disturbance
Author :
Li, Chunguang ; Liao, Xiaofeng
Author_Institution :
Centre for Nonlinear & Complex Syst., Univ. of Electron. Sci. & Technol. of China
Volume :
53
Issue :
10
fYear :
2006
Firstpage :
2265
Lastpage :
2273
Abstract :
Neural networks suffer from the natural intra- and inter-cellular noise perturbations and environmental fluctuations. Such noises will undoubtedly affect the dynamics of the neural networks both quantitatively and qualitatively. In this paper, we study the effects of noise perturbations on the stability and periodicity of delayed recurrent neural networks. We first derive the mean-square stability conditions for stochastic delayed recurrent neural networks without and with parametric uncertainties, respectively. After that, we study the stochastic periodicity (stability) with disturbance attenuation of delayed recurrent neural networks. The analysis are all based on the Lyapunov-Krasovskii functional approach, and the conditions are all expressed in terms of linear matrix inequalities, which can be easily solved by using the effective convex optimization techniques. Several numerical examples are also given to demonstrate the correctness and effectiveness of the theoretical results
Keywords :
Lyapunov methods; linear matrix inequalities; noise; perturbation techniques; recurrent neural nets; stability; Lyapunov-Krasovskii functional approach; convex optimization; delayed recurrent neural networks; environmental fluctuations; linear matrix inequality; mean-square stability; noise disturbance; noise perturbations; robust periodicity; robust stability; stochastic periodicity; Attenuation; Delay effects; Fluctuations; Neural networks; Noise robustness; Recurrent neural networks; Robust stability; Stochastic resonance; Uncertainty; Working environment noise; Disturbance; linear matrix inequality (LMI); neural network; noise; periodicity; stability;
fLanguage :
English
Journal_Title :
Circuits and Systems I: Regular Papers, IEEE Transactions on
Publisher :
ieee
ISSN :
1549-8328
Type :
jour
DOI :
10.1109/TCSI.2006.883159
Filename :
1710206
Link To Document :
بازگشت