Learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms

The pattern classification problem in machine learning algorithms is the task of assigning objects to one of a different predefined group of categories related to that object. Among the successful machine learning methods are Artificial Neural Networks (ANNs), which aim to minimize the error rate of...

Full description

Saved in:

Bibliographic Details
Main Author:	Elsayed, Ashraf Osman Ibrahim
Format:	Thesis
Language:	English
Published:	2015
Subjects:	QA75 Electronic computers Computer science
Online Access:	http://eprints.utm.my/id/eprint/54893/1/AshrafOsmanIbrahimPFC2015.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.54893
record_format	uketd_dc
spelling	my-utm-ep.548932020-11-15T09:28:21Z Learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms 2015-06 Elsayed, Ashraf Osman Ibrahim QA75 Electronic computers. Computer science The pattern classification problem in machine learning algorithms is the task of assigning objects to one of a different predefined group of categories related to that object. Among the successful machine learning methods are Artificial Neural Networks (ANNs), which aim to minimize the error rate of the training data and generate a simple network architecture to obtain a high classification accuracy. However, designing the ANN architecture is difficult due to the complexity of the structure, such as the network structure, number of hidden nodes and adjustment of weights. Therefore, a number of Evolutionary Algorithms (EAs) has been proposed to improve these network complexities. These algorithms are meant to optimize the connection weight, network structure, network error rate and classification accuracy. Nevertheless, these algorithms are implemented to optimize only one objective, despite the importance of executing many objectives simultaneously. Therefore, this study proposes simultaneous learning and structure optimization for designing a Three-term Backpropagation (TBP) network with four variants of Elitist Multi-objective Evolutionary Algorithms (EMOEAs). These include the Elitist Multi-objective Genetic Algorithm (EMOGA), Hybrid Elitist Multi-objective Genetic Algorithm (HEMOGA), Memetic Adaptive Elitist Multi-objective Genetic Algorithm (MAEMOGA) and the Elitist Multi-objective Differential Evolution (EMODE). The proposed methods are developed to evolve towards a Pareto-optimal set that is defined by multi-objective optimization consisting of connection weight, error rate and structural complexity of the network. The proposed methods are tested on binary and multi-class pattern classification problems. The results show that the proposed MAEMOGA and EMODE are better than EMOGA and HEMOGA in obtaining simple network structure and classification accuracy. 2015-06 Thesis http://eprints.utm.my/id/eprint/54893/ http://eprints.utm.my/id/eprint/54893/1/AshrafOsmanIbrahimPFC2015.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:94640 phd doctoral Universiti Teknologi Malaysia, Faculty of Computing Faculty of Computing
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA75 Electronic computers Computer science
spellingShingle	QA75 Electronic computers Computer science Elsayed, Ashraf Osman Ibrahim Learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms
description	The pattern classification problem in machine learning algorithms is the task of assigning objects to one of a different predefined group of categories related to that object. Among the successful machine learning methods are Artificial Neural Networks (ANNs), which aim to minimize the error rate of the training data and generate a simple network architecture to obtain a high classification accuracy. However, designing the ANN architecture is difficult due to the complexity of the structure, such as the network structure, number of hidden nodes and adjustment of weights. Therefore, a number of Evolutionary Algorithms (EAs) has been proposed to improve these network complexities. These algorithms are meant to optimize the connection weight, network structure, network error rate and classification accuracy. Nevertheless, these algorithms are implemented to optimize only one objective, despite the importance of executing many objectives simultaneously. Therefore, this study proposes simultaneous learning and structure optimization for designing a Three-term Backpropagation (TBP) network with four variants of Elitist Multi-objective Evolutionary Algorithms (EMOEAs). These include the Elitist Multi-objective Genetic Algorithm (EMOGA), Hybrid Elitist Multi-objective Genetic Algorithm (HEMOGA), Memetic Adaptive Elitist Multi-objective Genetic Algorithm (MAEMOGA) and the Elitist Multi-objective Differential Evolution (EMODE). The proposed methods are developed to evolve towards a Pareto-optimal set that is defined by multi-objective optimization consisting of connection weight, error rate and structural complexity of the network. The proposed methods are tested on binary and multi-class pattern classification problems. The results show that the proposed MAEMOGA and EMODE are better than EMOGA and HEMOGA in obtaining simple network structure and classification accuracy.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Elsayed, Ashraf Osman Ibrahim
author_facet	Elsayed, Ashraf Osman Ibrahim
author_sort	Elsayed, Ashraf Osman Ibrahim
title	Learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms
title_short	Learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms
title_full	Learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms
title_fullStr	Learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms
title_full_unstemmed	Learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms
title_sort	learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms
granting_institution	Universiti Teknologi Malaysia, Faculty of Computing
granting_department	Faculty of Computing
publishDate	2015
url	http://eprints.utm.my/id/eprint/54893/1/AshrafOsmanIbrahimPFC2015.pdf
_version_	1747817749388722176

Learning enhancement of three-term backpropagation network based on elitist multi-objective evolutionary algorithms

Similar Items