DocumentCode :
2649391
Title :
Input-to-state stability of recurrent neural networks with time-varying delays and Markovian switching
Author :
Xu, Yong ; Zhu, Song
Author_Institution :
Sch. of Math. Sci. & Comput. Technol., Central South Univ., Changsha, China
fYear :
2012
fDate :
23-25 May 2012
Firstpage :
1897
Lastpage :
1900
Abstract :
This paper presents an algebraic criterion for the input-to-state stability (ISS) of recurrent neural networks with Markovian switching. The criterion is easy to be verified with the connection weights. A numerical example is given to demonstrate the effectiveness of the proposed criteria.
Keywords :
Markov processes; algebra; delays; recurrent neural nets; stability; time-varying systems; ISS; Markovian switching; algebraic criterion; connection weights; input-to-state stability; recurrent neural networks; time-varying delays; Asymptotic stability; Delay; Recurrent neural networks; Stability criteria; Switches; Input-to-State stability; Markov Chain; Recurrent Neural Network; Time-Varying Delay;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control and Decision Conference (CCDC), 2012 24th Chinese
Conference_Location :
Taiyuan
Print_ISBN :
978-1-4577-2073-4
Type :
conf
DOI :
10.1109/CCDC.2012.6243023
Filename :
6243023
Link To Document :
بازگشت