DocumentCode
1648932
Title
New Results for Globally Asymptotic Stability and Instability of Recurrent Neural Networks
Author
Yutian, Zhang ; Qi, Luo
Author_Institution
Nanjing Univ. of Inf. Sci. & Technol., Nanjing
fYear
2007
Firstpage
162
Lastpage
166
Abstract
This paper presents four new theorems of globally asymptotic stability and instability for a general class of continuous-time recurrent neural networks with variant delay. With weaker conditions and less restrictive activation function, the obtained stability results improve and extend existing ones. Discussion and examples are given to illustrate and compare the new results with the old ones.
Keywords
asymptotic stability; continuous time systems; delays; recurrent neural nets; continuous-time recurrent neural networks; globally asymptotic instability; globally asymptotic stability; variant delay; Asymptotic stability; Educational institutions; Electronic mail; Equations; Information science; Mathematics; Neural networks; Physics; Recurrent neural networks; Symmetric matrices; Globally Asymptotic Stability; Instability; Recurrent Neural Networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Control Conference, 2007. CCC 2007. Chinese
Conference_Location
Hunan
Print_ISBN
978-7-81124-055-9
Electronic_ISBN
978-7-900719-22-5
Type
conf
DOI
10.1109/CHICC.2006.4347239
Filename
4347239
Link To Document