Study of cost functions in three term backpropagation for classification problems

Three Term Backpropagation was proposed in 2003 by Zweiri, and has outperformed standard Two Term Backpropagation. However, further studies on Three Term Backpropagation in 2007 indicated that the network only surpassed standard BP for small scale datasets (below 100 instances) but not for medium an...

Full description

Saved in:

Bibliographic Details
Main Author:	Kuppusamy, Puspadevi
Format:	Thesis
Language:	English
Published:	2008
Subjects:	QA75 Electronic computers Computer science
Online Access:	http://eprints.utm.my/id/eprint/9459/1/PuspadeviKuppusamyFSKSM2008.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.9459
record_format	uketd_dc
spelling	my-utm-ep.94592018-07-19T01:38:54Z Study of cost functions in three term backpropagation for classification problems 2008-10 Kuppusamy, Puspadevi QA75 Electronic computers. Computer science Three Term Backpropagation was proposed in 2003 by Zweiri, and has outperformed standard Two Term Backpropagation. However, further studies on Three Term Backpropagation in 2007 indicated that the network only surpassed standard BP for small scale datasets (below 100 instances) but not for medium and large scale datasets (above 100 instances). It has also been observed that by using Mean Square Error (MSE) as a cost function in Three Term Backpropagation network, has some drawbacks such as incorrect saturation and tend to trap in local minima, resulting in slow convergence and poor performance. In this study, substantial experiments on implementing various cost functions on Three Term BP are executed to probe the effectiveness of this network. The performance is measured in terms of convergence time and accuracy. The costs functions involve in this study include Mean Square Error, Bernoulli function, Modified cost function and Improved cost function. These cost functions were introduced by previous researchers. The outcome indicates that MSE is not an ideal cost function to be used for Three Term BP. Besides that, the results have also illustrated that improve cost functionâ€™s converges faster, while modified cost function produces high accuracy in classification 2008-10 Thesis http://eprints.utm.my/id/eprint/9459/ http://eprints.utm.my/id/eprint/9459/1/PuspadeviKuppusamyFSKSM2008.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:686?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
spellingShingle	QA75 Electronic computers Computer science Kuppusamy, Puspadevi Study of cost functions in three term backpropagation for classification problems
description	Three Term Backpropagation was proposed in 2003 by Zweiri, and has outperformed standard Two Term Backpropagation. However, further studies on Three Term Backpropagation in 2007 indicated that the network only surpassed standard BP for small scale datasets (below 100 instances) but not for medium and large scale datasets (above 100 instances). It has also been observed that by using Mean Square Error (MSE) as a cost function in Three Term Backpropagation network, has some drawbacks such as incorrect saturation and tend to trap in local minima, resulting in slow convergence and poor performance. In this study, substantial experiments on implementing various cost functions on Three Term BP are executed to probe the effectiveness of this network. The performance is measured in terms of convergence time and accuracy. The costs functions involve in this study include Mean Square Error, Bernoulli function, Modified cost function and Improved cost function. These cost functions were introduced by previous researchers. The outcome indicates that MSE is not an ideal cost function to be used for Three Term BP. Besides that, the results have also illustrated that improve cost functionâ€™s converges faster, while modified cost function produces high accuracy in classification
format	Thesis
qualification_level	Master's degree
author	Kuppusamy, Puspadevi
author_facet	Kuppusamy, Puspadevi
author_sort	Kuppusamy, Puspadevi
title	Study of cost functions in three term backpropagation for classification problems
title_short	Study of cost functions in three term backpropagation for classification problems
title_full	Study of cost functions in three term backpropagation for classification problems
title_fullStr	Study of cost functions in three term backpropagation for classification problems
title_full_unstemmed	Study of cost functions in three term backpropagation for classification problems
title_sort	study of cost functions in three term backpropagation for classification problems
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/9459/1/PuspadeviKuppusamyFSKSM2008.pdf
_version_	1747814735024226304

Study of cost functions in three term backpropagation for classification problems

Similar Items