DocumentCode
2743052
Title
On State-Space Neural Networks for Systems Identification: Stability and Complexity
Author
Gil, P. ; Henriques, J. ; Dourado, A. ; Duarte-Ramos, H.
Author_Institution
Centre for Informatics & Syst., Coimbra Univ.
fYear
2006
fDate
7-9 June 2006
Firstpage
1
Lastpage
5
Abstract
The problem of order estimation and global stability in affine three-layered state-space neural networks is here addressed. An upper bound for the number of neurons to be inserted in the hidden layer is computed using a subspace technique. Some sufficient conditions for the global asymptotic stability are presented using the Lyapunov stability theory and the contraction mapping theorem
Keywords
Lyapunov methods; asymptotic stability; computational complexity; identification; neural nets; state-space methods; Lyapunov stability; contraction mapping theorem; global asymptotic stability; hidden layer; order estimation; state-space neural network; subspace technique; system identification; Artificial neural networks; Asymptotic stability; Bifurcation; Feedforward neural networks; Network topology; Neural networks; Neurons; Nonlinear dynamical systems; Recurrent neural networks; System identification; State-space neural networks; complexity; stability;
fLanguage
English
Publisher
ieee
Conference_Titel
Cybernetics and Intelligent Systems, 2006 IEEE Conference on
Conference_Location
Bangkok
Print_ISBN
1-4244-0023-6
Type
conf
DOI
10.1109/ICCIS.2006.252333
Filename
4017892
Link To Document