DocumentCode
1553284
Title
On the analysis of neural networks with asymmetric connection weights or noninvertible transfer functions
Author
Liang, Ping ; Xiong, Kaiqi
Author_Institution
Dept. of Electr. Eng., California Univ., Riverside, CA, USA
Volume
29
Issue
5
fYear
1999
fDate
10/1/1999 12:00:00 AM
Firstpage
632
Lastpage
636
Abstract
This paper extends the energy function to the analysis of the stability of neural networks with asymmetric interconnections and noninvertible transfer functions. Based on the new energy function, stability theorems and convergent criteria are derived which improve the available results in the literature. A simpler proof of a previous result for complete stability is given. Theorems on complete stability of neural networks with noninvertible output functions are presented
Keywords
neural nets; stability; transfer functions; asymmetric connection weights; convergent criteria; neural networks; noninvertible output functions; noninvertible transfer functions; stability; Cellular neural networks; Differential equations; Hopfield neural networks; Neural networks; Neurons; Recurrent neural networks; Stability analysis; Stability criteria; Symmetric matrices; Transfer functions;
fLanguage
English
Journal_Title
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
Publisher
ieee
ISSN
1083-4419
Type
jour
DOI
10.1109/3477.790447
Filename
790447
Link To Document