{"id":{"repo_id":"cork","oai_identifier":"oai:cora.ucc.ie:10468/10564"},"canonical_url":"https://search.dev.ndltd.org/etd/cork/oai:cora.ucc.ie:10468/10564","repository":{"repo_id":"cork","name":"University College Cork","base_url":"https://cora.ucc.ie/server/oai/request"},"display":{"title":"Parameter reduction in deep learning and classification","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.","abstract_html":"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.","abstract_has_math":false,"creators":["Browne, David"],"institution":"University College Cork","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Prestwich, Steven David"],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-02-20","date_published":"2020-02-20","updated_at":"2026-07-24T01:48:18Z","subjects":["Classification","AlexNet","VGG16","CIFAR","Deep learning","Feature selection","Network pruning","Supervised learning","Unsupervised Kmeans","Machine learning","Random forest","Support vector machines","Image recognition","Microarray data","Gene selection","Credit scoring","High-dimensional data"],"languages":["en"],"rights":["© 2020, David Browne."],"rights_urls":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10468/10564","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Prestwich, Steven David"]},{"key":"dc:creator","label":"Author","values":["Browne, David"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-09-22T09:59:01Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-09-22T09:59:01Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-02-20"]},{"key":"dc:publisher","label":"Institution","values":["University College Cork"]},{"key":"dc:type","label":"Dc Type","values":["Doctoral thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["PhD - Doctor of Philosophy"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Classification","AlexNet","VGG16","CIFAR","Deep learning","Feature selection","Network pruning","Supervised learning","Unsupervised Kmeans","Machine learning","Random forest","Support vector machines","Image recognition","Microarray data","Gene selection","Credit scoring","High-dimensional data"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["© 2020, David Browne."]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10468/10564"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Parameter reduction in deep learning and classification"]}]}],"canonical_facts":{"dc:contributor.advisor":["Prestwich, Steven David"],"dc:creator":["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: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."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10468/10564"],"dc:language.iso":["en"],"dc:publisher":["University College Cork"],"dc:rights":["© 2020, David Browne."],"dc:rights.uri":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:subject":["Classification","AlexNet","VGG16","CIFAR","Deep learning","Feature selection","Network pruning","Supervised learning","Unsupervised Kmeans","Machine learning","Random forest","Support vector machines","Image recognition","Microarray data","Gene selection","Credit scoring","High-dimensional data"],"dc:title":["Parameter reduction in deep learning and classification"],"dc:type":["Doctoral thesis"],"dc:type.qualificationlevel":["Doctoral"],"dc:type.qualificationname":["PhD - Doctor of Philosophy"]},"updated_at":"2026-07-24T01:48:18Z"}