Show simple item record

dc.contributor.authorAn, Senjian
dc.contributor.authorHayat, M.
dc.contributor.authorKhan, S.
dc.contributor.authorBennamoun, M.
dc.contributor.authorBoussaid, F.
dc.contributor.authorSohel, F.
dc.identifier.citationAn, S. and Hayat, M. and Khan, S. and Bennamoun, M. and Boussaid, F. and Sohel, F. 2015. Contractive rectifier networks for nonlinear maximum margin classification, pp. 2515-2523.

© 2015 IEEE. To find the optimal nonlinear separating boundary with maximum margin in the input data space, this paper proposes Contractive Rectifier Networks (CRNs), wherein the hidden-layer transformations are restricted to be contraction mappings. The contractive constraints ensure that the achieved separating margin in the input space is larger than or equal to the separating margin in the output layer. The training of the proposed CRNs is formulated as a linear support vector machine (SVM) in the output layer, combined with two or more contractive hidden layers. Effective algorithms have been proposed to address the optimization challenges arising from contraction constraints. Experimental results on MNIST, CIFAR-10, CIFAR-100 and MIT-67 datasets demonstrate that the proposed contractive rectifier networks consistently outperform their conventional unconstrained rectifier network counterparts.

dc.titleContractive rectifier networks for nonlinear maximum margin classification
dc.typeConference Paper
dcterms.source.volume2015 International Conference on Computer Vision, ICCV 2015
dcterms.source.titleProceedings of the IEEE International Conference on Computer Vision
dcterms.source.seriesProceedings of the IEEE International Conference on Computer Vision
curtin.departmentSchool of Electrical Engineering, Computing and Mathematical Science (EECMS)
curtin.accessStatusFulltext not available

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record