Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/164770
Title: Unsupervised generative variational continual learning
Authors: Liu, Guimeng
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2023
Publisher: Nanyang Technological University
Source: Liu, G. (2023). Unsupervised generative variational continual learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/164770
Abstract: Continual 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.
URI: https://hdl.handle.net/10356/164770
DOI: 10.1109/ICIP46576.2022.9897538
Schools: School of Electrical and Electronic Engineering 
Organisations: Agency for Science, Technology and Research (A*STAR)
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
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 17, 2024

Download(s)

11
Updated on Jul 17, 2024

Google ScholarTM

Check

Altmetric


Plumx

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