DocumentCode
897618
Title
Learning a simple recurrent neural state space model to behave like Chua´s double scroll
Author
Suykens, Johan A K ; Vandewalle, Joos
Author_Institution
Dept. of Electr. Eng., Katholieke Univ., Leuven, Belgium
Volume
42
Issue
8
fYear
1995
fDate
8/1/1995 12:00:00 AM
Firstpage
499
Lastpage
502
Abstract
The authors present a simple discrete time autonomous neural state space model (recurrent network) that behaves like Chua´s double scroll. The model is identified using Narendra´s dynamic back propagation procedure. Learning is done in “packets” of increasing time horizon
Keywords
Chua´s circuit; backpropagation; chaos; circuit stability; discrete time systems; identification; nonlinear network analysis; nonlinear systems; recurrent neural nets; state-space methods; Chua double scroll; discrete time autonomous model; dynamic back propagation procedure; recurrent network; recurrent neural state space model; Asymptotic stability; Circuit stability; Linear algebra; Matrices; Neural networks; Nonlinear systems; Polynomials; State-space methods; Sufficient conditions; Testing;
fLanguage
English
Journal_Title
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
Publisher
ieee
ISSN
1057-7122
Type
jour
DOI
10.1109/81.404066
Filename
404066
Link To Document