Particle swarm optimization for neural network learning enhancement

Backpropagation (BP) algorithm is widely used to solve many real world problems by using the concept of Multilayer Perceptron (MLP). However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. To overcome this problem, Genetic Algorith...

Full description

Saved in:

Bibliographic Details
Main Author:	Abdull Hamed, Haza Nuzly
Format:	Thesis
Language:	English
Published:	2006
Subjects:	QA75 Electronic computers Computer science
Online Access:	http://eprints.utm.my/id/eprint/5381/1/HazaNuzlyAbdullHamedMFSKSM2006.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.5381
record_format	uketd_dc
spelling	my-utm-ep.53812018-03-07T20:59:26Z Particle swarm optimization for neural network learning enhancement 2006-06 Abdull Hamed, Haza Nuzly QA75 Electronic computers. Computer science Backpropagation (BP) algorithm is widely used to solve many real world problems by using the concept of Multilayer Perceptron (MLP). However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. To overcome this problem, Genetic Algorithm (GA) has been used to determine optimal value for BP parameters such as learning rate and momentum rate and also for weight optimization. In Backpropagation Neural Network (BPNN), there are many elements to be considered such as the number of input, hidden and output nodes, learning rate, momentum rate, bias, minimum error and activation/transfer functions. All these elements will affect the speed of neural network learning. Although GA is successfully improved BPNN learning, there are still some issues such as longer training time to produce the output and usage of complex functions in selection, crossover and mutation calculation. In this study, the latest optimization algorithm, Particle Swarm Optimization (PSO) is chosen and applied in feedforward neural network to enhance the learning process in terms of convergence rate and classification accuracy. Two programs have been developed; Particle Swarm Optimization Feedforward Neural Network (PSONN) and Genetic Algorithm Backpropagation Neural Network (GANN). The results show that PSONN give promising results in term of convergence rate and classification compared to GANN. 2006-06 Thesis http://eprints.utm.my/id/eprint/5381/ http://eprints.utm.my/id/eprint/5381/1/HazaNuzlyAbdullHamedMFSKSM2006.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 Abdull Hamed, Haza Nuzly Particle swarm optimization for neural network learning enhancement
description	Backpropagation (BP) algorithm is widely used to solve many real world problems by using the concept of Multilayer Perceptron (MLP). However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. To overcome this problem, Genetic Algorithm (GA) has been used to determine optimal value for BP parameters such as learning rate and momentum rate and also for weight optimization. In Backpropagation Neural Network (BPNN), there are many elements to be considered such as the number of input, hidden and output nodes, learning rate, momentum rate, bias, minimum error and activation/transfer functions. All these elements will affect the speed of neural network learning. Although GA is successfully improved BPNN learning, there are still some issues such as longer training time to produce the output and usage of complex functions in selection, crossover and mutation calculation. In this study, the latest optimization algorithm, Particle Swarm Optimization (PSO) is chosen and applied in feedforward neural network to enhance the learning process in terms of convergence rate and classification accuracy. Two programs have been developed; Particle Swarm Optimization Feedforward Neural Network (PSONN) and Genetic Algorithm Backpropagation Neural Network (GANN). The results show that PSONN give promising results in term of convergence rate and classification compared to GANN.
format	Thesis
qualification_level	Master's degree
author	Abdull Hamed, Haza Nuzly
author_facet	Abdull Hamed, Haza Nuzly
author_sort	Abdull Hamed, Haza Nuzly
title	Particle swarm optimization for neural network learning enhancement
title_short	Particle swarm optimization for neural network learning enhancement
title_full	Particle swarm optimization for neural network learning enhancement
title_fullStr	Particle swarm optimization for neural network learning enhancement
title_full_unstemmed	Particle swarm optimization for neural network learning enhancement
title_sort	particle swarm optimization 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	2006
url	http://eprints.utm.my/id/eprint/5381/1/HazaNuzlyAbdullHamedMFSKSM2006.pdf
_version_	1747814587881750528

Particle swarm optimization for neural network learning enhancement

Similar Items