Please use this identifier to cite or link to this item:
Title: Parameter estimation of sigmoid superpositions: Dynamical system approach
Authors: Tyukin, Ivan Yu.
van Leeuwen, Cees
Prokhorov, D.V.
First Published: 2003
Publisher: Massachusetts Institute of Technology Press (MIT Press)
Citation: Neural Computation, 2003, 15 (10), pp.2419-2455
Abstract: Superposition of sigmoid function over a finite time interval is shown to be equivalent to the linear combination of the solutions of a linearly parameterized system of logistic differential equations. Due to the linearity with respect to the parameters of the system, it is possible to design an effective procedure for parameter adjustment. Stability properties of this procedure are analyzed.
DOI Link: 10.1162/089976603322362428
ISSN: 0899-7667
eISSN: 1530-888X
Version: Publisher version
Status: Peer reviewed
Type: Article
Rights: Copyright © 2003 Massachusetts Institute of Technology (MIT). Deposited with reference to the publisher's archiving policy available on the SHERPA/RoMEO website.
Appears in Collections:Published Articles, Dept. of Mathematics

Files in This Item:
File Description SizeFormat 
8948810_amended.pdf1.71 MBAdobe PDFView/Open

Items in LRA are protected by copyright, with all rights reserved, unless otherwise indicated.