Parameter reduction in deep learning and classification

Simple item page
dc.availability.bitstreamopenaccess
dc.contributor.advisorPrestwich, Steven Daviden
dc.contributor.authorBrowne, David
dc.contributor.funderScience Foundation Irelanden
dc.date.accessioned2020-09-22T09:59:01Z
dc.date.available2020-09-22T09:59:01Z
dc.date.issued2020-02-20
dc.date.submitted2020-02-20
dc.description.abstractThe goal of this thesis is to develop methods to reduce model and problem complexity in the area of classification tasks. Whether it is a traditional or a deep learning classification task, decreasing complexity helps to greatly improve efficiency, and also adds regularization to the models. In traditional machine learning, high-dimensionality can cause models to over-fit the training data, and hence not generalize well, while in deep learning, neural networks have shown to achieve state-of-the-art results, especially in the area of image recognition, in their current state cannot be easily deployed on memory restricted Internet-of-Things devices. Although much work has been carried out on dimensionality reduction, the first part of our work focuses on using dominancy between features in the aim to select a relevant subset of informative features. We propose 3 variations, with different benefits, including fast filter features selection and a hybrid filter-wrapper approach. In the second section, dedicated to deep learning, our work focuses on pruning methods to extract an overall much more efficient neural network. We show that our proposed techniques outperform previous state-of-the-art methods, across the different classification areas on a number of benchmark datasets using various classifiers and neural networks.en
dc.description.statusNot peer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationBrowne, D. 2020. Parameter reduction in deep learning and classification. PhD Thesis, University College Cork.en
dc.identifier.endpage198en
dc.identifier.urihttps://hdl.handle.net/10468/10564
dc.language.isoenen
dc.publisherUniversity College Corken
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2289/IE/INSIGHT - Irelands Big Data and Analytics Research Centre/en
dc.rights© 2020, David Browne.en
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectClassificationen
dc.subjectAlexNeten
dc.subjectVGG16en
dc.subjectCIFARen
dc.subjectDeep learningen
dc.subjectFeature selectionen
dc.subjectNetwork pruningen
dc.subjectSupervised learningen
dc.subjectUnsupervised Kmeansen
dc.subjectMachine learningen
dc.subjectRandom foresten
dc.subjectSupport vector machinesen
dc.subjectImage recognitionen
dc.subjectMicroarray dataen
dc.subjectGene selectionen
dc.subjectCredit scoringen
dc.subjectHigh-dimensional dataen
dc.titleParameter reduction in deep learning and classificationen
dc.typeDoctoral thesisen
dc.type.qualificationlevelDoctoralen
dc.type.qualificationnamePhD - Doctor of Philosophyen
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
David Browne Parameter Reduction in Deep Learning and Classification.pdf
Size:
77.21 MB
Format:
Adobe Portable Document Format
Description:
Full Text E-thesis
Download
Thumbnail Image
Name:
3. 110715117 - David John Browne - Submission for Examination.pdf
Size:
390.89 KB
Format:
Adobe Portable Document Format
Description:
Submission for Examination Form
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
5.2 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Theses
College of Science, Engineering and Food Science - Doctoral Theses
Computer Science - Doctoral Theses
Insight Centre for Data Analytics - Doctoral Theses