Theories and Perspectives on Practical Deep Learning

Simple item page
dc.contributor.advisorKyrillidis, Anastasiosen_US
dc.creatorWolfe, Cameron Ronalden_US
dc.date.accessioned2023-09-01T19:56:50Zen_US
dc.date.available2023-09-01T19:56:50Zen_US
dc.date.created2023-08en_US
dc.date.issued2023-07-05en_US
dc.date.submittedAugust 2023en_US
dc.date.updated2023-09-01T19:56:50Zen_US
dc.description.abstractDeep neural networks (DNNs) have proven to be adept at accurately automating many tasks (e.g., image and text classification, object detection, text generation, and more). Across most domains, DNNs tend to achieve better performance with increasing scale, both in terms of dataset and model size. As such, the benefit of DNNs comes at a steep computational (and monetary) cost, which can limit their applicability. This document aims to identify novel and intuitive techniques that can make deep learning more usable across domains and communities.en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationWolfe, Cameron Ronald. "Theories and Perspectives on Practical Deep Learning." (2023) Diss., Rice University. https://hdl.handle.net/1911/115248.en_US
dc.identifier.urihttps://hdl.handle.net/1911/115248en_US
dc.language.isoengen_US
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.subjectneural networksen_US
dc.subjectpruningen_US
dc.subjectdistributed trainingen_US
dc.subjecthyperparameter tuningen_US
dc.subjectonline learningen_US
dc.subjectstreaming learningen_US
dc.titleTheories and Perspectives on Practical Deep Learningen_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentComputer Scienceen_US
thesis.degree.disciplineEngineeringen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelDoctoralen_US
thesis.degree.nameDoctor of Philosophyen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
WOLFE-DOCUMENT-2023.pdf
Size:
4.14 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.98 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Theses and Dissertations