Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/164770
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLiu, Guimengen_US
dc.date.accessioned2023-02-14T02:31:24Z-
dc.date.available2023-02-14T02:31:24Z-
dc.date.issued2023-
dc.identifier.citationLiu, G. (2023). Unsupervised generative variational continual learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/164770en_US
dc.identifier.urihttps://hdl.handle.net/10356/164770-
dc.description.abstractContinual learning aims at learning a sequence of tasks without forgetting any task. There are mainly three categories in this field: replay methods, regularization-based methods, and parameter isolation methods. Recent research in continual learning generally incorporates two of these methods to obtain better performance. This dissertation combined regularization-based methods and parameter isolation methods to ensure the important parameters for each task do not change drastically and free up unimportant parameters so the network is capable to learn new knowledge. While most of the existing literature on continual learning is aimed at class incremental learning in a supervised setting, there is enormous potential for unsupervised continual learning using generative models. This dissertation proposes a combination of architectural pruning and network expansion in generative variational models toward unsupervised generative continual learning (UGCL). Evaluations on standard benchmark data sets demonstrate the superior generative ability of the proposed method.en_US
dc.language.isoenen_US
dc.publisherNanyang Technological Universityen_US
dc.subjectEngineering::Electrical and electronic engineeringen_US
dc.titleUnsupervised generative variational continual learningen_US
dc.typeThesis-Master by Courseworken_US
dc.contributor.supervisorPonnuthurai Nagaratnam Suganthanen_US
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.description.degreeMaster of Science (Computer Control and Automation)en_US
dc.contributor.organizationAgency for Science, Technology and Research (A*STAR)en_US
dc.identifier.doi10.1109/ICIP46576.2022.9897538en_US
dc.contributor.supervisoremailEPNSugan@ntu.edu.sgen_US
item.fulltextWith Fulltext-
item.grantfulltextrestricted-
Appears in Collections:EEE Theses
Files in This Item:
File Description SizeFormat 
Unsupervised generative variational continual learning.pdf
  Restricted Access
4.44 MBAdobe PDFView/Open

Page view(s)

200
Updated on Jul 12, 2024

Download(s)

11
Updated on Jul 12, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.