An Adaptive Learning Rate for RBFNN Using Time-Domain Feedback Analysis

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Syed Saad Azhar Ali, Muhammad Moinuddin, Kamran Raza, Syed Hasan Adil
Format: Article
Language:English
Published: Wiley 2014-01-01
Series:The Scientific World Journal
Online Access:http://dx.doi.org/10.1155/2014/850189
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849411818841178112
author Syed Saad Azhar Ali
Muhammad Moinuddin
Kamran Raza
Syed Hasan Adil
author_facet Syed Saad Azhar Ali
Muhammad Moinuddin
Kamran Raza
Syed Hasan Adil
author_sort Syed Saad Azhar Ali
collection DOAJ
description 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 l2 stability governed by the upper bounding via small gain theorem. Simulation results are presented to support our theoretical development.
format Article
id doaj-art-5a5ab236f4e140f28c636f17bb4877a9
institution Kabale University
issn 2356-6140
1537-744X
language English
publishDate 2014-01-01
publisher Wiley
record_format Article
series The Scientific World Journal
spelling doaj-art-5a5ab236f4e140f28c636f17bb4877a92025-08-20T03:34:40ZengWileyThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/850189850189An Adaptive Learning Rate for RBFNN Using Time-Domain Feedback AnalysisSyed Saad Azhar Ali0Muhammad Moinuddin1Kamran Raza2Syed Hasan Adil3Department of Electrical and Electronic Engineering, Universiti Teknologi Petronas, Bandar Seri Iskandar, 31750 Tronoh, Perak, MalaysiaFaculty of Engineering, Sciences and Technology, Iqra University, Defence View, Karachi 75500, PakistanFaculty of Engineering, Sciences and Technology, Iqra University, Defence View, Karachi 75500, PakistanFaculty of Engineering, Sciences and Technology, Iqra University, Defence View, Karachi 75500, PakistanRadial 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 l2 stability governed by the upper bounding via small gain theorem. Simulation results are presented to support our theoretical development.http://dx.doi.org/10.1155/2014/850189
spellingShingle Syed Saad Azhar Ali
Muhammad Moinuddin
Kamran Raza
Syed Hasan Adil
An Adaptive Learning Rate for RBFNN Using Time-Domain Feedback Analysis
The Scientific World Journal
title An Adaptive Learning Rate for RBFNN Using Time-Domain Feedback Analysis
title_full An Adaptive Learning Rate for RBFNN Using Time-Domain Feedback Analysis
title_fullStr An Adaptive Learning Rate for RBFNN Using Time-Domain Feedback Analysis
title_full_unstemmed An Adaptive Learning Rate for RBFNN Using Time-Domain Feedback Analysis
title_short An Adaptive Learning Rate for RBFNN Using Time-Domain Feedback Analysis
title_sort adaptive learning rate for rbfnn using time domain feedback analysis
url http://dx.doi.org/10.1155/2014/850189
work_keys_str_mv AT syedsaadazharali anadaptivelearningrateforrbfnnusingtimedomainfeedbackanalysis
AT muhammadmoinuddin anadaptivelearningrateforrbfnnusingtimedomainfeedbackanalysis
AT kamranraza anadaptivelearningrateforrbfnnusingtimedomainfeedbackanalysis
AT syedhasanadil anadaptivelearningrateforrbfnnusingtimedomainfeedbackanalysis
AT syedsaadazharali adaptivelearningrateforrbfnnusingtimedomainfeedbackanalysis
AT muhammadmoinuddin adaptivelearningrateforrbfnnusingtimedomainfeedbackanalysis
AT kamranraza adaptivelearningrateforrbfnnusingtimedomainfeedbackanalysis
AT syedhasanadil adaptivelearningrateforrbfnnusingtimedomainfeedbackanalysis