Parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization

Evolving Spiking Neural Network (ESNN) is widely used in classification problem. However, ESNN like any other neural networks is incapable to find its own parameter optimum values, which are crucial for classification accuracy. Thus, in this study, ESNN is integrated with an improved Particle Swarm...

Full description

Saved in:

Bibliographic Details
Main Author:	Md. Said, Nur Nadiah
Format:	Thesis
Language:	English
Published:	2018
Subjects:	QA75 Electronic computers Computer science
Online Access:	http://eprints.utm.my/id/eprint/81484/1/NurNadiahMdSaidMFC2018.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.81484
record_format	uketd_dc
spelling	my-utm-ep.814842019-08-23T05:19:05Z Parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization 2018 Md. Said, Nur Nadiah QA75 Electronic computers. Computer science Evolving Spiking Neural Network (ESNN) is widely used in classification problem. However, ESNN like any other neural networks is incapable to find its own parameter optimum values, which are crucial for classification accuracy. Thus, in this study, ESNN is integrated with an improved Particle Swarm Optimization (PSO) known as Dynamic Population Particle Swarm Optimization (DPPSO) to optimize the ESNN parameters: the modulation factor (Mod), similarity factor (Sim) and threshold factor (C). To find the optimum ESNN parameter value, DPPSO uses a dynamic population that removes the lowest particle value in every pre-defined iteration. The integration of ESNN-DPPSO facilitates the ESNN parameter optimization searching during the training stage. The performance analysis is measured by classification accuracy and is compared with the existing method. Five datasets gained from University of California Irvine (UCI) Machine Learning Repository are used for this study. The experimental result presents better accuracy compared to the existing technique and thus improves the ESNN method in optimising its parameter values. 2018 Thesis http://eprints.utm.my/id/eprint/81484/ http://eprints.utm.my/id/eprint/81484/1/NurNadiahMdSaidMFC2018.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:119781 masters Universiti Teknologi Malaysia Computing
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA75 Electronic computers Computer science
spellingShingle	QA75 Electronic computers Computer science Md. Said, Nur Nadiah Parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization
description	Evolving Spiking Neural Network (ESNN) is widely used in classification problem. However, ESNN like any other neural networks is incapable to find its own parameter optimum values, which are crucial for classification accuracy. Thus, in this study, ESNN is integrated with an improved Particle Swarm Optimization (PSO) known as Dynamic Population Particle Swarm Optimization (DPPSO) to optimize the ESNN parameters: the modulation factor (Mod), similarity factor (Sim) and threshold factor (C). To find the optimum ESNN parameter value, DPPSO uses a dynamic population that removes the lowest particle value in every pre-defined iteration. The integration of ESNN-DPPSO facilitates the ESNN parameter optimization searching during the training stage. The performance analysis is measured by classification accuracy and is compared with the existing method. Five datasets gained from University of California Irvine (UCI) Machine Learning Repository are used for this study. The experimental result presents better accuracy compared to the existing technique and thus improves the ESNN method in optimising its parameter values.
format	Thesis
qualification_level	Master's degree
author	Md. Said, Nur Nadiah
author_facet	Md. Said, Nur Nadiah
author_sort	Md. Said, Nur Nadiah
title	Parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization
title_short	Parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization
title_full	Parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization
title_fullStr	Parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization
title_full_unstemmed	Parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization
title_sort	parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization
granting_institution	Universiti Teknologi Malaysia
granting_department	Computing
publishDate	2018
url	http://eprints.utm.my/id/eprint/81484/1/NurNadiahMdSaidMFC2018.pdf
_version_	1747818341422071808

Parameter optimization of evolving spiking neural network with dynamic population particle swarm optimization

Similar Items