Continual learning in human activity recognition: an empirical analysis of regularization

Saurav Jha, Martin Schiemer*, Juan Ye

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

4 Downloads (Pure)

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.
Original languageEnglish
Pages1-4
Number of pages4
Publication statusPublished - 17 Jul 2020
EventThirty-seventh International Conference on Machine Learning, ICML 2020; ICML Workshop on Continual Learning -
Duration: 13 Jul 202018 Jul 2020
Conference number: 37
https://icml.cc/Conferences/2020/ScheduleMultitrack?event=5743 (Link to Workshop)

Workshop

WorkshopThirty-seventh International Conference on Machine Learning, ICML 2020; ICML Workshop on Continual Learning
Abbreviated titleICML 2020
Period13/07/2018/07/20
Internet address

Fingerprint

Dive into the research topics of 'Continual learning in human activity recognition: an empirical analysis of regularization'. Together they form a unique fingerprint.

Cite this