DocumentCode :
1341558
Title :
Delay-Slope-Dependent Stability Results of Recurrent Neural Networks
Author :
Tao Li ; Wei Xing Zheng ; Chong Lin
Author_Institution :
Dept. of Inf. & Commun., Nanjing Univ. of Inf. Sci. & Technol., Nanjing, China
Volume :
22
Issue :
12
fYear :
2011
Firstpage :
2138
Lastpage :
2143
Abstract :
By using the fact that the neuron activation functions are sector bounded and nondecreasing, this brief presents a new method, named the delay-slope-dependent method, for stability analysis of a class of recurrent neural networks with time-varying delays. This method includes more information on the slope of neuron activation functions and fewer matrix variables in the constructed Lyapunov-Krasovskii functional. Then some improved delay-dependent stability criteria with less computational burden and conservatism are obtained. Numerical examples are given to illustrate the effectiveness and the benefits of the proposed method.
Keywords :
Lyapunov methods; delays; recurrent neural nets; stability criteria; time-varying systems; constructed Lyapunov-Krasovskii functional; delay-slope-dependent method; delay-slope-dependent stability criteria; neuron activation function; recurrent neural network; time-varying delay; Asymptotic stability; Delay; Neurons; Recurrent neural networks; Stability analysis; Asymptotic stability; delay-slope-dependent; recurrent neural networks; Algorithms; Computer Simulation; Models, Theoretical; Neural Networks (Computer);
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/TNN.2011.2169425
Filename :
6035791
Link To Document :
بازگشت