Record Details

Asymptotic Behaviour of Gradient Learning Algorithms in Neural Network Models for the Identification of Nonlinear Systems

Репозитарій Національного Авіаційного Університету

View Archive Info
 
 
Field Value
 
Title Asymptotic Behaviour of Gradient Learning Algorithms in Neural Network Models for the Identification of Nonlinear Systems
 
Creator Azarskov, V.N.
Kucherov, D.P.
Nikolaienko, S.A.
Zhiteckii, L.S.
 
Subject neural network
 
Description This paper deals with studying the asymptotical properties of multilayer neural networks models used for the
adaptive identification of wide class of nonlinearly parameterized systems in stochastic environment. To adjust the neural network’s weights, the standard online gradient type learning algorithms are employed. The learning set is assumed to be infinite but bounded. The Lyapunov-like tool is utilized to analyze the ultimate behaviour of learning processes in the presence of stochastic input variables. New sufficient conditions guaranteeing the global convergence of these algorithms in the stochastic frameworks are derived. The main their feature is that they need no a penalty term to achieve the boundedness of weight sequence. To demonstrate asymptotic behaviour of the learning algorithms and support the theoretical studies, some simulation examples are also given.
 
Date 2016-03-25T21:01:40Z
2016-03-25T21:01:40Z
2015-07-27
 
Type Article
 
Identifier 2469-7400
10.11648/j.ajnna.20150101.11
 
Language en
 
Format application/pdf
 
Publisher Science Publishing Group
 

Технічна підтримка: НДІІТТ НАУ