Tuning of the structure and parameters of a neural network using an improved genetic algorithm

Leung, FHF; Lam, HK; Ling, SH; Tam, PKS

Tuning of the structure and parameters of a neural network using an improved genetic algorithm

Leung, FHF Lam, HK Ling, SH

Tam, PKS

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Neural Networks, 2003, 14 (1), pp. 79 - 88
Issue Date:: 2003-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download full textAdobe PDF (549.49 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Leung, FHF	en_US
dc.contributor.author	Lam, HK	en_US
dc.contributor.author	Ling, SH https://orcid.org/0000-0003-0849-5098	en_US
dc.contributor.author	Tam, PKS	en_US
dc.date.issued	2003-01-01	en_US
dc.identifier.citation	IEEE Transactions on Neural Networks, 2003, 14 (1), pp. 79 - 88	en_US
dc.identifier.issn	1045-9227	en_US
dc.identifier.uri	http://hdl.handle.net/10453/15148
dc.description.abstract	This paper presents the tuning of the structure and parameters of a neural network using an improved genetic algorithm (GA). It will also be shown that the improved GA performs better than the standard GA based on some benchmark test functions. A neural network with switches introduced to its links is proposed. By doing this, the proposed neural network can learn both the input-output relationships of an application and the network structure using the improved GA. The number of hidden nodes is chosen manually by increasing it from a small number until the learning performance in terms of fitness value is good enough. Application examples on sunspot forecasting and associative memory are given to show the merits of the improved GA and the proposed neural network.	en_US
dc.relation.ispartof	IEEE Transactions on Neural Networks	en_US
dc.relation.isbasedon	10.1109/TNN.2002.804317	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Tuning of the structure and parameters of a neural network using an improved genetic algorithm	en_US
dc.type	Journal Article
utslib.citation.volume	1	en_US
utslib.citation.volume	14	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
dc.location.activity	WOS:000180862400008	en_US
dc.location.activity	WOS:000289456000009
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Biomedical Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CHT - Health Technologies
utslib.copyright.status	open_access
pubs.issue	1	en_US
pubs.publication-status	Published	en_US
pubs.volume	14	en_US

Abstract:

This paper presents the tuning of the structure and parameters of a neural network using an improved genetic algorithm (GA). It will also be shown that the improved GA performs better than the standard GA based on some benchmark test functions. A neural network with switches introduced to its links is proposed. By doing this, the proposed neural network can learn both the input-output relationships of an application and the network structure using the improved GA. The number of hidden nodes is chosen manually by increasing it from a small number until the learning performance in terms of fitness value is good enough. Application examples on sunspot forecasting and associative memory are given to show the merits of the improved GA and the proposed neural network.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/15148