Three-term backpropagation algorithm for classification problem

Standard Backpropagation Algorithm (BP) is a widely used algorithm in training Neural Network that is proven to be very successful in many diverse application. This algorithm utilizes two term parameters which are Learning Rate, Î± and Momentum Factor,Î². Despite the general success of this algorit...

Full description

Saved in:

Bibliographic Details
Main Author:	Saman, Fadhlina Izzah
Format:	Thesis
Language:	English
Published:	2006
Subjects:	QA75 Electronic computers Computer science
Online Access:	http://eprints.utm.my/id/eprint/4062/1/FadhlinaIzzahSamanMFSKSM2006.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.4062
record_format	uketd_dc
spelling	my-utm-ep.40622018-01-15T02:14:48Z Three-term backpropagation algorithm for classification problem 2006-04 Saman, Fadhlina Izzah QA75 Electronic computers. Computer science Standard Backpropagation Algorithm (BP) is a widely used algorithm in training Neural Network that is proven to be very successful in many diverse application. This algorithm utilizes two term parameters which are Learning Rate, Î± and Momentum Factor,Î². Despite the general success of this algorithm, there are several drawbacks and limitations which some of them are the existence of local minima, slow rates of convergence and some of the modification of BP algorithm requires complex and costly calculations at each iteration, which offset their faster rates of convergence. To overcome this problem, a third learning parameter, Proportional Factor (Î³) has been proposed by Zweiri et. al., (2003). This new algorithm is called Three-Term BP. This study investigates the performance of Three-Term BP and compares its performance with standard BP. To achieve this objective, experiments were conducted by implementing Three-Term BP to three dataset which are Balloon, Iris and Cancer dataset. These datasets represents small, medium and large scale data respectively. The results obtained showed that Three-Term BP only outperforms standard BP while using small scale data but not in case of medium and large dataset. This might be caused by the instability of the network while using medium and large dataset as it has been proven in analysis part of the study. 2006-04 Thesis http://eprints.utm.my/id/eprint/4062/ http://eprints.utm.my/id/eprint/4062/1/FadhlinaIzzahSamanMFSKSM2006.pdf application/pdf en public 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 Saman, Fadhlina Izzah Three-term backpropagation algorithm for classification problem
description	Standard Backpropagation Algorithm (BP) is a widely used algorithm in training Neural Network that is proven to be very successful in many diverse application. This algorithm utilizes two term parameters which are Learning Rate, Î± and Momentum Factor,Î². Despite the general success of this algorithm, there are several drawbacks and limitations which some of them are the existence of local minima, slow rates of convergence and some of the modification of BP algorithm requires complex and costly calculations at each iteration, which offset their faster rates of convergence. To overcome this problem, a third learning parameter, Proportional Factor (Î³) has been proposed by Zweiri et. al., (2003). This new algorithm is called Three-Term BP. This study investigates the performance of Three-Term BP and compares its performance with standard BP. To achieve this objective, experiments were conducted by implementing Three-Term BP to three dataset which are Balloon, Iris and Cancer dataset. These datasets represents small, medium and large scale data respectively. The results obtained showed that Three-Term BP only outperforms standard BP while using small scale data but not in case of medium and large dataset. This might be caused by the instability of the network while using medium and large dataset as it has been proven in analysis part of the study.
format	Thesis
qualification_level	Master's degree
author	Saman, Fadhlina Izzah
author_facet	Saman, Fadhlina Izzah
author_sort	Saman, Fadhlina Izzah
title	Three-term backpropagation algorithm for classification problem
title_short	Three-term backpropagation algorithm for classification problem
title_full	Three-term backpropagation algorithm for classification problem
title_fullStr	Three-term backpropagation algorithm for classification problem
title_full_unstemmed	Three-term backpropagation algorithm for classification problem
title_sort	three-term backpropagation algorithm for classification problem
granting_institution	Universiti Teknologi Malaysia, Faculty of Computer Science and Information System
granting_department	Faculty of Computer Science and Information System
publishDate	2006
url	http://eprints.utm.my/id/eprint/4062/1/FadhlinaIzzahSamanMFSKSM2006.pdf
_version_	1747814491986329600

Three-term backpropagation algorithm for classification problem

Similar Items