Files in this item
Continual learning in human activity recognition : an empirical analysis of regularization
Item metadata
dc.contributor.author | Jha, Saurav | |
dc.contributor.author | Schiemer, Martin | |
dc.contributor.author | Ye, Juan | |
dc.date.accessioned | 2020-07-13T16:30:07Z | |
dc.date.available | 2020-07-13T16:30:07Z | |
dc.date.issued | 2020-07-17 | |
dc.identifier | 275504871 | |
dc.identifier | a5929b35-91af-4a9f-9338-fcfc66e90c44 | |
dc.identifier.citation | Jha , S , Schiemer , M & Ye , J 2020 , ' Continual learning in human activity recognition : an empirical analysis of regularization ' , Paper presented at Thirty-seventh International Conference on Machine Learning, ICML 2020; ICML Workshop on Continual Learning , 13/07/20 - 18/07/20 pp. 1-4 . | en |
dc.identifier.citation | workshop | en |
dc.identifier.other | ORCID: /0000-0002-2838-6836/work/98784917 | |
dc.identifier.uri | https://hdl.handle.net/10023/20242 | |
dc.description.abstract | Given the growing trend of continual learning techniques for deep neural networks focusing on the domain of computer vision, there is a need to identify which of these generalizes well to other tasks such as human activity recognition (HAR). As recent methods have mostly been composed of loss regularization terms and memory replay, we provide a constituent-wise analysis of some prominent task-incremental learning techniques employing these on HAR datasets. We find that most regularization approaches lack substantial effect and provide an intuition of when they fail. Thus, we make the case that the development of continual learning algorithms should be motivated by rather diverse task domains. | |
dc.format.extent | 4 | |
dc.format.extent | 557700 | |
dc.language.iso | eng | |
dc.relation.ispartof | en | |
dc.subject | QA75 Electronic computers. Computer science | en |
dc.subject | T Technology | en |
dc.subject | 3rd-DAS | en |
dc.subject.lcc | QA75 | en |
dc.subject.lcc | T | en |
dc.title | Continual learning in human activity recognition : an empirical analysis of regularization | en |
dc.type | Conference paper | en |
dc.contributor.institution | University of St Andrews. School of Computer Science | en |
dc.description.status | Peer reviewed | en |
dc.identifier.url | https://sites.google.com/view/cl-icml/accepted-papers | en |
This item appears in the following Collection(s)
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.