The tuning of error signal for back-propagation algorithms

Despite of Back-propagation (BP) algorithm existence for almost four decades, it is still widely used in many fields to solve range of real world problems. However, it suffers from slow convergence and tends to trap in local minima. So, an improved two-term error function is proposed to overcome the...

Full description

Saved in:

Bibliographic Details
Main Author:	Rengasamy, Renugah
Format:	Thesis
Language:	English
Published:	2008
Subjects:	QA75 Electronic computers Computer science QA Mathematics
Online Access:	http://eprints.utm.my/id/eprint/9460/1/VikneshRamamoorthyMFSKSM2008.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.9460
record_format	uketd_dc
spelling	my-utm-ep.94602018-07-19T01:38:55Z The tuning of error signal for back-propagation algorithms 2008-10 Rengasamy, Renugah QA75 Electronic computers. Computer science QA Mathematics Despite of Back-propagation (BP) algorithm existence for almost four decades, it is still widely used in many fields to solve range of real world problems. However, it suffers from slow convergence and tends to trap in local minima. So, an improved two-term error function is proposed to overcome the existing problems. This new algorithm is proven to be a better algorithm. The main purpose of this study is to evaluate the efficiency of improved two-term error function by applying three different values of ÃŸ parameter in the activation function. The improved twoterm error with different error signal (d ) will replace the conventional error signal in standard BP. These both algorithms will be tested on three universal datasets; Iris, Balloon and Cancer by comparing the accuracy and the convergence speed. The ultimate outcome of the study would be handful information to get a better justification on these both Back-propagation algorithms usages in real application. 2008-10 Thesis http://eprints.utm.my/id/eprint/9460/ http://eprints.utm.my/id/eprint/9460/1/VikneshRamamoorthyMFSKSM2008.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:693?site_name=Restricted Repository masters Universiti Teknologi Malaysia, Faculty of Computer Science and Information System Faculty of Computer Science and Information System
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA75 Electronic computers Computer science QA Mathematics
spellingShingle	QA75 Electronic computers Computer science QA Mathematics Rengasamy, Renugah The tuning of error signal for back-propagation algorithms
description	Despite of Back-propagation (BP) algorithm existence for almost four decades, it is still widely used in many fields to solve range of real world problems. However, it suffers from slow convergence and tends to trap in local minima. So, an improved two-term error function is proposed to overcome the existing problems. This new algorithm is proven to be a better algorithm. The main purpose of this study is to evaluate the efficiency of improved two-term error function by applying three different values of ÃŸ parameter in the activation function. The improved twoterm error with different error signal (d ) will replace the conventional error signal in standard BP. These both algorithms will be tested on three universal datasets; Iris, Balloon and Cancer by comparing the accuracy and the convergence speed. The ultimate outcome of the study would be handful information to get a better justification on these both Back-propagation algorithms usages in real application.
format	Thesis
qualification_level	Master's degree
author	Rengasamy, Renugah
author_facet	Rengasamy, Renugah
author_sort	Rengasamy, Renugah
title	The tuning of error signal for back-propagation algorithms
title_short	The tuning of error signal for back-propagation algorithms
title_full	The tuning of error signal for back-propagation algorithms
title_fullStr	The tuning of error signal for back-propagation algorithms
title_full_unstemmed	The tuning of error signal for back-propagation algorithms
title_sort	tuning of error signal for back-propagation algorithms
granting_institution	Universiti Teknologi Malaysia, Faculty of Computer Science and Information System
granting_department	Faculty of Computer Science and Information System
publishDate	2008
url	http://eprints.utm.my/id/eprint/9460/1/VikneshRamamoorthyMFSKSM2008.pdf
_version_	1747814735268544512

The tuning of error signal for back-propagation algorithms

Similar Items