Show simple item record

dc.contributor.authorAljarah, Ibrahim
dc.contributor.authorFaris, Hossam
dc.contributor.authorMirjalili, Seyedali
dc.contributor.authorAl-Madi, Nailah
dc.date.accessioned2018-07-19T05:09:29Z
dc.date.available2018-07-19T05:09:29Z
dc.date.issued2018
dc.identifier.issn0941-0643
dc.identifier.doi10.1007/s00521-016-2559-2
dc.identifier.urihttp://hdl.handle.net/10072/142997
dc.description.abstractTraining artificial neural networks is considered as one of the most challenging machine learning problems. This is mainly due to the presence of a large number of solutions and changes in the search space for different datasets. Conventional training techniques mostly suffer from local optima stagnation and degraded convergence, which make them impractical for datasets with many features. The literature shows that stochastic population-based optimization techniques suit this problem better and are reliably alternative because of high local optima avoidance and flexibility. For the first time, this work proposes a new learning mechanism for radial basis function networks based on biogeography-based optimizer as one of the most well-regarded optimizers in the literature. To prove the efficacy of the proposed methodology, it is employed to solve 12 well-known datasets and compared to 11 current training algorithms including gradient-based and stochastic approaches. The paper considers changing the number of neurons and investigating the performance of algorithms on radial basis function networks with different number of parameters as well. A statistical test is also conducted to judge about the significance of the results. The results show that the biogeography-based optimizer trainer is able to substantially outperform the current training algorithms on all datasets in terms of classification accuracy, speed of convergence, and entrapment in local optima. In addition, the comparison of trainers on radial basis function networks with different neurons size reveal that the biogeography-based optimizer trainer is able to train radial basis function networks with different number of structural parameters effectively.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherSpringer
dc.relation.ispartofpagefrom1
dc.relation.ispartofpageto25
dc.relation.ispartofjournalNeural Computing and Applications
dc.subject.fieldofresearchArtificial Intelligence and Image Processing not elsewhere classified
dc.subject.fieldofresearchArtificial Intelligence and Image Processing
dc.subject.fieldofresearchCognitive Sciences
dc.subject.fieldofresearchElectrical and Electronic Engineering
dc.subject.fieldofresearchcode080199
dc.subject.fieldofresearchcode0801
dc.subject.fieldofresearchcode1702
dc.subject.fieldofresearchcode0906
dc.titleTraining radial basis function networks using biogeography-based optimizer
dc.typeJournal article
dc.type.descriptionC1 - Articles
dc.type.codeC - Journal Articles
gro.description.notepublicThis publication has been entered into Griffith Research Online as an Advanced Online Version.
gro.hasfulltextNo Full Text
gro.griffith.authorMirjalili, Seyedali


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record