Show simple item record

dc.contributor.advisorMcCane, Brendan
dc.contributor.authorSzymanski, Lech
dc.date.available2012-03-02T02:42:33Z
dc.date.copyright2012
dc.identifier.citationSzymanski, L. (2012). Deep architectures and classification by intermediary transformations (Thesis, Doctor of Philosophy). University of Otago. Retrieved from http://hdl.handle.net/10523/2129en
dc.identifier.urihttp://hdl.handle.net/10523/2129
dc.description.abstractWith the development of deep belief nets, the empirical evidence supporting a link between deep architecture neural networks and generalisation with respect to classification has been mounting. An analytical proof of this relation would have an immense impact on machine learning and classification, yet it has not been forthcoming due to the limited understanding of what constitutes an appropriate internal data representation in a multi-layer neural network model that would be conducive to good classification. This work proposes a theory of intermediary transformations, which establishes an objective for an individual layer in a deep architecture classifier that improves data separability according to its class labels. A training algorithm, based on the new theory, for a multi-layer neural network is proposed and evaluated against traditional backpropagation and deep belief net learning. The results confirm that a supervised classification training objective for an individual hidden layer is viable and generalises well. Classification by intermediary transformations offers new directions and insights in the quest to illuminate the black box model of deep architectures.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherUniversity of Otago
dc.rightsAll items in OUR Archive are provided for private study and research purposes and are protected by copyright with all rights reserved unless otherwise indicated.
dc.subjectMachine learning
dc.subjectClassification
dc.subjectDeep architectures
dc.titleDeep architectures and classification by intermediary transformations
dc.typeThesis
dc.date.updated2012-03-02T01:29:43Z
dc.language.rfc3066en
thesis.degree.disciplineComputer Science
thesis.degree.nameDoctor of Philosophy
thesis.degree.grantorUniversity of Otago
thesis.degree.levelDoctoral
otago.openaccessOpen
 Find in your library

Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record