Show simple item record

Files in this item


Item metadata

dc.contributor.authorJha, Saurav
dc.contributor.authorSchiemer, Martin
dc.contributor.authorYe, Juan
dc.identifier.citationJha , 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.otherPURE: 275504871
dc.identifier.otherPURE UUID: a5929b35-91af-4a9f-9338-fcfc66e90c44
dc.identifier.otherORCID: /0000-0002-2838-6836/work/98784917
dc.description.abstractGiven 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.rightsCopyright © 2020 the Author(s). This work has been made available online in accordance with publisher policies or with permission. Permission for further reuse of this content should be sought from the publisher or the rights holder. This is the author created accepted manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectT Technologyen
dc.titleContinual learning in human activity recognition : an empirical analysis of regularizationen
dc.typeConference paperen
dc.contributor.institutionUniversity of St Andrews. School of Computer Scienceen
dc.description.statusPeer revieweden

This item appears in the following Collection(s)

Show simple item record