Bacterial foraging optmization algorithm for neural network learning enhancement

Backpropagation algorithm is used to solve many real world problems using the concept of Multilayer Perceptron. However, main disadvantages of Backpropagation are its convergence rate is relatively slow, and it is often trapped at the local minima. To solve this problem, in literatures, evolutionary...

Full description

Saved in:

Bibliographic Details
Main Author:	Al-Qasem Al-Hadi, Ismail Ahmed
Format:	Thesis
Language:	English
Published:	2011
Subjects:	QA75 Electronic computers Computer science
Online Access:	http://eprints.utm.my/id/eprint/32824/5/IsmailAhmedAlQasemAl-HadiMFSKSM2011.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.32824
record_format	uketd_dc
spelling	my-utm-ep.328242018-05-27T07:55:12Z Bacterial foraging optmization algorithm for neural network learning enhancement 2011 Al-Qasem Al-Hadi, Ismail Ahmed QA75 Electronic computers. Computer science Backpropagation algorithm is used to solve many real world problems using the concept of Multilayer Perceptron. However, main disadvantages of Backpropagation are its convergence rate is relatively slow, and it is often trapped at the local minima. To solve this problem, in literatures, evolutionary algorithms such as Particle Swarm Optimization algorithm has been applied in feedforward neural network to optimize the learning process in terms of convergence rate and classification accuracy but this process needs longer training time. To provide alternative solution, in this study, Bacteria Foraging Optimization Algorithm has been selected and applied in feedforward neural network to enhance the learning process in terms of convergence rate and classification accuracy. One of the main processes in Bacteria Foraging Optimization algorithm is the chemotactic movement of a virtual bacterium that makes a trial solution of the optimization problem. This process of chemotactic movement is guided to make the learning process of Artificial Neural Network faster. The developed Bacteria Foraging Optimization Algorithm Feedforward Neural Network (BFOANN) is compared against Particle Swarm Optimization Feedforward Neural Network (PSONN). The results show that BFOANN gave better performance in terms of convergence rate and classification accuracy compared to PSONN. 2011 Thesis http://eprints.utm.my/id/eprint/32824/ http://eprints.utm.my/id/eprint/32824/5/IsmailAhmedAlQasemAl-HadiMFSKSM2011.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 Al-Qasem Al-Hadi, Ismail Ahmed Bacterial foraging optmization algorithm for neural network learning enhancement
description	Backpropagation algorithm is used to solve many real world problems using the concept of Multilayer Perceptron. However, main disadvantages of Backpropagation are its convergence rate is relatively slow, and it is often trapped at the local minima. To solve this problem, in literatures, evolutionary algorithms such as Particle Swarm Optimization algorithm has been applied in feedforward neural network to optimize the learning process in terms of convergence rate and classification accuracy but this process needs longer training time. To provide alternative solution, in this study, Bacteria Foraging Optimization Algorithm has been selected and applied in feedforward neural network to enhance the learning process in terms of convergence rate and classification accuracy. One of the main processes in Bacteria Foraging Optimization algorithm is the chemotactic movement of a virtual bacterium that makes a trial solution of the optimization problem. This process of chemotactic movement is guided to make the learning process of Artificial Neural Network faster. The developed Bacteria Foraging Optimization Algorithm Feedforward Neural Network (BFOANN) is compared against Particle Swarm Optimization Feedforward Neural Network (PSONN). The results show that BFOANN gave better performance in terms of convergence rate and classification accuracy compared to PSONN.
format	Thesis
qualification_level	Master's degree
author	Al-Qasem Al-Hadi, Ismail Ahmed
author_facet	Al-Qasem Al-Hadi, Ismail Ahmed
author_sort	Al-Qasem Al-Hadi, Ismail Ahmed
title	Bacterial foraging optmization algorithm for neural network learning enhancement
title_short	Bacterial foraging optmization algorithm for neural network learning enhancement
title_full	Bacterial foraging optmization algorithm for neural network learning enhancement
title_fullStr	Bacterial foraging optmization algorithm for neural network learning enhancement
title_full_unstemmed	Bacterial foraging optmization algorithm for neural network learning enhancement
title_sort	bacterial foraging optmization algorithm for neural network learning enhancement
granting_institution	Universiti Teknologi Malaysia, Faculty of Computer Science and Information System
granting_department	Faculty of Computer Science and Information System
publishDate	2011
url	http://eprints.utm.my/id/eprint/32824/5/IsmailAhmedAlQasemAl-HadiMFSKSM2011.pdf
_version_	1747816069373886464

Bacterial foraging optmization algorithm for neural network learning enhancement

Similar Items