DocumentCode
3110037
Title
Error passivation to filtering for a general class of switched recurrent neural networks with noise disturbance
Author
Liu, Jiqing ; Huang, Jinhua
Author_Institution
Dept. of Electr. & Electron. Eng., Wuhan Inst. of Shipbuilding Technol., Wuhan, China
fYear
2011
fDate
26-28 March 2011
Firstpage
839
Lastpage
842
Abstract
In this paper, error passivation to filtering is considered for a general class of switched recurrent neural networks with noise disturbance. Based on Lyapunov-Krasovskii stability theory, and linear matrix inequality, a new sufficient criterion is established such that the filtering error system is globally asymptotically stable and passive from the noise disturbance to the output error, which can be easily facilitated by using some standard numerical packages.
Keywords
Lyapunov methods; asymptotic stability; filtering theory; linear matrix inequalities; recurrent neural nets; time-varying systems; Lyapunov-Krasovskii stability theory; error passivation; filtering error system; linear matrix inequality; noise disturbance; numerical packages; switched recurrent neural networks; Artificial neural networks; Neurons; Noise; Recurrent neural networks; Stability analysis; State estimation; Switches;
fLanguage
English
Publisher
ieee
Conference_Titel
Information Science and Technology (ICIST), 2011 International Conference on
Conference_Location
Nanjing
Print_ISBN
978-1-4244-9440-8
Type
conf
DOI
10.1109/ICIST.2011.5765110
Filename
5765110
Link To Document