Parameter reduction in deep learning and classification

Show simple item record

dc.contributor.advisor Prestwich, Steven David en
dc.contributor.author Browne, David
dc.date.accessioned 2020-09-22T09:59:01Z
dc.date.available 2020-09-22T09:59:01Z
dc.date.issued 2020-02-20
dc.date.submitted 2020-02-20
dc.identifier.citation Browne, D. 2020. Parameter reduction in deep learning and classification. PhD Thesis, University College Cork. en
dc.identifier.endpage 198 en
dc.identifier.uri http://hdl.handle.net/10468/10564
dc.description.abstract The 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.format.mimetype application/pdf en
dc.language.iso en en
dc.publisher University College Cork en
dc.rights © 2020, David Browne. en
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/ en
dc.subject Classification en
dc.subject AlexNet en
dc.subject VGG16 en
dc.subject CIFAR en
dc.subject Deep learning en
dc.subject Feature selection en
dc.subject Network pruning en
dc.subject Supervised learning en
dc.subject Unsupervised Kmeans en
dc.subject Machine learning en
dc.subject Random forest en
dc.subject Support vector machines en
dc.subject Image recognition en
dc.subject Microarray data en
dc.subject Gene selection en
dc.subject Credit scoring en
dc.subject High-dimensional data en
dc.title Parameter reduction in deep learning and classification en
dc.type Doctoral thesis en
dc.type.qualificationlevel Doctoral en
dc.type.qualificationname PhD - Doctor of Philosophy en
dc.internal.availability Full text available en
dc.description.version Accepted Version en
dc.contributor.funder Science Foundation Ireland en
dc.description.status Not peer reviewed en
dc.internal.school Computer Science and Information Technology en
dc.internal.conferring Autumn 2020 en
dc.internal.ricu Insight - Centre for Data Analytics en
dc.relation.project info:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2289/IE/INSIGHT - Irelands Big Data and Analytics Research Centre/ en
dc.availability.bitstream openaccess


Files in this item

This item appears in the following Collection(s)

Show simple item record

© 2020, David Browne. Except where otherwise noted, this item's license is described as © 2020, David Browne.
This website uses cookies. By using this website, you consent to the use of cookies in accordance with the UCC Privacy and Cookies Statement. For more information about cookies and how you can disable them, visit our Privacy and Cookies statement