Continual learning and data analysis of time series data

Time-series data finds wide usage among various field, making it a common and useful type of data. However, Catastrophic forgetting arise when model is optimizing for the new task, which in real-life case can be different data distribution. While most of the continual learning strategies focus...

Full description

Saved in:

Bibliographic Details
Main Author:	Ye, Songyi
Other Authors:	Soh Yeng Chai
Format:	Final Year Project
Language:	English
Published:	Nanyang Technological University 2023
Subjects:	Engineering::Electrical and electronic engineering
Online Access:	https://hdl.handle.net/10356/167635
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-167635
record_format	dspace
spelling	sg-ntu-dr.10356-1676352023-07-07T17:50:28Z Continual learning and data analysis of time series data Ye, Songyi Soh Yeng Chai School of Electrical and Electronic Engineering EYCSOH@ntu.edu.sg Engineering::Electrical and electronic engineering Time-series data finds wide usage among various field, making it a common and useful type of data. However, Catastrophic forgetting arise when model is optimizing for the new task, which in real-life case can be different data distribution. While most of the continual learning strategies focus on static data, this project aims to explore the feasibility of the most used strategy Elastic Weight Container (EWC) on time-series data. This project uses a Human Activity Recognition problem as a benchmark. EWC is then implemented on the model to compare the loss of accuracy with and without it. The result shows the extend of continual learning EWC can achieve on time series data. Bachelor of Engineering (Electrical and Electronic Engineering) 2023-05-31T05:13:34Z 2023-05-31T05:13:34Z 2023 Final Year Project (FYP) Ye, S. (2023). Continual learning and data analysis of time series data. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/167635 https://hdl.handle.net/10356/167635 en application/pdf Nanyang Technological University
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	Engineering::Electrical and electronic engineering
spellingShingle	Engineering::Electrical and electronic engineering Ye, Songyi Continual learning and data analysis of time series data
description	Time-series data finds wide usage among various field, making it a common and useful type of data. However, Catastrophic forgetting arise when model is optimizing for the new task, which in real-life case can be different data distribution. While most of the continual learning strategies focus on static data, this project aims to explore the feasibility of the most used strategy Elastic Weight Container (EWC) on time-series data. This project uses a Human Activity Recognition problem as a benchmark. EWC is then implemented on the model to compare the loss of accuracy with and without it. The result shows the extend of continual learning EWC can achieve on time series data.
author2	Soh Yeng Chai
author_facet	Soh Yeng Chai Ye, Songyi
format	Final Year Project
author	Ye, Songyi
author_sort	Ye, Songyi
title	Continual learning and data analysis of time series data
title_short	Continual learning and data analysis of time series data
title_full	Continual learning and data analysis of time series data
title_fullStr	Continual learning and data analysis of time series data
title_full_unstemmed	Continual learning and data analysis of time series data
title_sort	continual learning and data analysis of time series data
publisher	Nanyang Technological University
publishDate	2023
url	https://hdl.handle.net/10356/167635
_version_	1772825653568077824

Continual learning and data analysis of time series data

Similar Items