eprintid: 5438
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/54/38
datestamp: 2023-11-09 16:17:10
lastmod: 2023-11-09 16:17:10
status_changed: 2023-11-09 16:01:40
type: article
metadata_visibility: show
creators_name: Ali, S.S.A.
creators_name: Moinuddin, M.
creators_name: Raza, K.
creators_name: Adil, S.H.
title: An adaptive learning rate for RBFNN using time-domain feedback analysis
ispublished: pub
keywords: article; computer simulation; controlled study; feedback system; learning algorithm; measurement error; nerve cell; nonlinear system; pattern recognition; radial based function; steady state; theoretical model; time series analysis; uncertainty; adaptive learning rate; Article; feedback system; prediction; radial basis function neural network; simulation; algorithm; artificial neural network, Algorithms; Feedback; Neural Networks (Computer)
note: cited By 21
abstract: Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control and time series prediction. In this paper, the learning algorithm of radial basis function neural networks is analyzed in a feedback structure. The robustness of the learning algorithm is discussed in the presence of uncertainties that might be due to noisy perturbations at the input or to modeling mismatch. An intelligent adaptation rule is developed for the learning rate of RBFNN which gives faster convergence via an estimate of error energy while giving guarantee to the l 2 stability governed by the upper bounding via small gain theorem. Simulation results are presented to support our theoretical development. © 2014 Syed Saad Azhar Ali et al.
date: 2014
publisher: ScientificWorld Ltd.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84897543058&doi=10.1155%2f2014%2f850189&partnerID=40&md5=80887e8df04e77b3bfbc35f665dd9de8
id_number: 10.1155/2014/850189
full_text_status: none
publication: The Scientific World Journal
volume: 2014
refereed: TRUE
issn: 1537744X
citation:   Ali, S.S.A. and Moinuddin, M. and Raza, K. and Adil, S.H.  (2014) An adaptive learning rate for RBFNN using time-domain feedback analysis.  The Scientific World Journal, 2014.   ISSN 1537744X