Show simple item record

dc.contributor.advisorSong, Le
dc.contributor.authorLiu, Weiyang
dc.date.accessioned2020-09-08T12:48:02Z
dc.date.available2020-09-08T12:48:02Z
dc.date.created2020-08
dc.date.issued2020-07-27
dc.date.submittedAugust 2020
dc.identifier.urihttp://hdl.handle.net/1853/63670
dc.description.abstractHow to efficiently learn discriminative deep features is arguably one of the core problems in deep learning, since it can benefit a lot of downstream tasks such as visual recognition, object detection, semantic segmentation, etc. In this dissertation, we present a unified deep representation learning framework on hypersphere, which inherently introduces a novel hyperspherical inductive bias into deep neural networks. We show that our framework is well motivated from both empirical observations and theories. We discuss our framework from four distinct perspectives: (1) learning objectives on hypersphere; (2) neural architectures on hypersphere; (3) regularizations on hypersphere; (4) hyperspherical training paradigm. From the first three perspectives, we explain how we can utilize the idea of hyperspherical learning to revisit and reinvent corresponding components in deep learning. From the last perspective, we propose a general neural training framework that is heavily inspired by hyperspherical learning. We conduct comprehensive experiments on many applications to demonstrate that our deep hyperspherical learning framework yields better generalization, faster convergence and stronger adversarial robustness compared to the standard deep learning framework.
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technology
dc.subjectMachine learning
dc.subjectVisual recognition
dc.subjectDeep learning
dc.subjectRepresentation learning
dc.subjectNeural networks
dc.subjectHypersphere
dc.titleDeep representation learning on hypersphere
dc.typeDissertation
dc.description.degreePh.D.
dc.contributor.departmentComputational Science and Engineering
thesis.degree.levelDoctoral
dc.contributor.committeeMemberRehg, James Matthew
dc.contributor.committeeMemberChau, Duen Horng
dc.contributor.committeeMemberXie, Yao
dc.contributor.committeeMemberRaj, Bhiksha
dc.date.updated2020-09-08T12:48:02Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record