Tuning the structure and parameters of a neural network using an orthogonal simulated annealing algorithm

Li Sun Shu*, Shinn-Ying Ho, Shinn Jang Ho

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

In this paper, an orthogonal simulated annealing algorithm (OSA) is applied to get an optimal network structure and parameters of a feedforward neural network at the same time. An orthogonal experimental design which based on OSA could efficiently generate large good candidate solutions by using a few computing cost. High performance of OSA-based method can be shown to efficiently obtain more accurate solution in prediction of the sunspot numbers problem, compare with other exited methods.

Original languageEnglish
Title of host publication2009 Joint Conferences on Pervasive Computing, JCPC 2009
Pages789-792
Number of pages4
DOIs
StatePublished - 1 Dec 2009
Event2009 Joint Conferences on Pervasive Computing, JCPC 2009 - Tamsui, Taipei, Taiwan
Duration: 3 Dec 20095 Dec 2009

Publication series

Name2009 Joint Conferences on Pervasive Computing, JCPC 2009

Conference

Conference2009 Joint Conferences on Pervasive Computing, JCPC 2009
CountryTaiwan
CityTamsui, Taipei
Period3/12/095/12/09

Fingerprint Dive into the research topics of 'Tuning the structure and parameters of a neural network using an orthogonal simulated annealing algorithm'. Together they form a unique fingerprint.

Cite this