Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/155416
Title: Modified-LwF method for continual learning
Authors: Dang, Zhang
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Dang, Z. (2021). Modified-LwF method for continual learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/155416
Abstract: In this dissertation, we show that it is possible to overcome the catastrophic forgetting with several different methods. What is more important is that our method remembers old tasks better by combining the original learning without forgetting and elastic weight consolidation, which is the main contribution that both the merits of elastic weight consolidation and learning without forgetting are put into one method (Modified LwF). Besides, the upper bound joint training method, fine tune, EWC and original LwF methods are experimented by adding the new tasks one by one. In this procedure, the paths of the training in the algorithm will be focused more on. We finally finished all four tasks, and the size of the fourth task is far bigger than the previous three.
URI: https://hdl.handle.net/10356/155416
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
论文(1).pdf
  Restricted Access
2.61 MBAdobe PDFView/Open

Page view(s)

79
Updated on Feb 7, 2023

Download(s)

2
Updated on Feb 7, 2023

Google ScholarTM

Check

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