Please use this identifier to cite or link to this item: http://er.nau.edu.ua/handle/NAU/28359
Title: Convergence Properties of an Online Learning Algorithm in Neural Network Models of Complex Systems
Authors: V.N.Azarskov
L.S. Zhiteckii
S. A. Nikolaienko
Keywords: nonlinear model; neural network; gradient algorithm; learning; convergence
Issue Date: Oct-2013
Publisher: ВД "Освіта України"
Abstract: Asymptotic behavior of the online gradient algorithm with a constant step size employed for learning in neural network models of nonlinear systems having hidden layer are studied. The sufficient conditions guaranteeing the convergence of this algorithm in the random environment are established
URI: http://er.nau.edu.ua/handle/NAU/28359
Appears in Collections:Матеріали конференцій кафедри аерокосмічних систем управління

Files in This Item:
File Description SizeFormat 
Azarskov_IEEE 2013 .pdf6.32 MBAdobe PDFView/Open


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