Active transfer learning for activity recognition

Tom Diethe; Niall Twomey; Peter Flach

Active transfer learning for activity recognition

Tom Diethe, Niall Twomey, Peter Flach

Research output: Contribution to conference › Conference Paper › peer-review

246 Downloads (Pure)

Abstract

We examine activity recognition from accelerometers, which provides at least two major challenges for machine learning. Firstly, the deployment context is likely to differ from the learning context. Secondly, accurate labelling of training data is time-consuming and error-prone. This calls for a combination of active and transfer learning. We derive a hierarchical Bayesian model that is a natural fit to such problems, and provide empirical validation on synthetic and publicly available datasets. The results show that by combining active and transfer learning, we can achieve faster learning with fewer labels on a target domain than by either alone.

Original language	English
Number of pages	6
Publication status	Published - 2016
Event	European Symposium on Artificial Neural Networks - Belgium, Bruges, United Kingdom Duration: 27 Apr 2016 → 29 Apr 2016

Conference

Conference	European Symposium on Artificial Neural Networks
Country/Territory	United Kingdom
City	Bruges
Period	27/04/16 → 29/04/16

Research Groups and Themes

Jean Golding
SPHERE

Keywords

active learning
transfer learning
smart home
accelerometers

Access to Document

Active_Transfer_camera_readyAccepted author manuscript, 321 KBLicence: CC BY

https://www.elen.ucl.ac.be/esann/proceedings/electronicproceedings.htm

Handle.net

Persistent link

SPHERE (EPSRC IRC)
Craddock, I. J. (Principal Investigator), Coyle, D. T. (Principal Investigator), Flach, P. A. (Principal Investigator), Kaleshi, D. (Principal Investigator), Mirmehdi, M. (Principal Investigator), Piechocki, R. J. (Principal Investigator), Stark, B. H. (Principal Investigator), Ascione, R. (Co-Principal Investigator), Ashburn, A. M. (Collaborator), Burnett, M. E. (Collaborator), Damen, D. (Co-Principal Investigator), Gooberman-Hill, R. (Principal Investigator), Harwin, W. S. (Collaborator), Hilton, G. (Co-Principal Investigator), Holderbaum, W. (Collaborator), Holley, A. P. (Manager), Manchester, V. A. (Administrator), Meller, B. J. (Other ), Stack, E. (Collaborator) & Gilchrist, I. D. (Principal Investigator)
1/10/13 → 30/09/18
Project: Research, Parent

Cite this

@conference{c462e875888745df9fe1179b958f8851,

title = "Active transfer learning for activity recognition",

abstract = "We examine activity recognition from accelerometers, which provides at least two major challenges for machine learning. Firstly, the deployment context is likely to differ from the learning context. Secondly, accurate labelling of training data is time-consuming and error-prone. This calls for a combination of active and transfer learning. We derive a hierarchical Bayesian model that is a natural fit to such problems, and provide empirical validation on synthetic and publicly available datasets. The results show that by combining active and transfer learning, we can achieve faster learning with fewer labels on a target domain than by either alone.",

keywords = "active learning, transfer learning, smart home, accelerometers",

author = "Tom Diethe and Niall Twomey and Peter Flach",

year = "2016",

language = "English",

note = "European Symposium on Artificial Neural Networks ; Conference date: 27-04-2016 Through 29-04-2016",

}

TY - CONF

T1 - Active transfer learning for activity recognition

AU - Diethe, Tom

AU - Twomey, Niall

AU - Flach, Peter

PY - 2016

Y1 - 2016

N2 - We examine activity recognition from accelerometers, which provides at least two major challenges for machine learning. Firstly, the deployment context is likely to differ from the learning context. Secondly, accurate labelling of training data is time-consuming and error-prone. This calls for a combination of active and transfer learning. We derive a hierarchical Bayesian model that is a natural fit to such problems, and provide empirical validation on synthetic and publicly available datasets. The results show that by combining active and transfer learning, we can achieve faster learning with fewer labels on a target domain than by either alone.

AB - We examine activity recognition from accelerometers, which provides at least two major challenges for machine learning. Firstly, the deployment context is likely to differ from the learning context. Secondly, accurate labelling of training data is time-consuming and error-prone. This calls for a combination of active and transfer learning. We derive a hierarchical Bayesian model that is a natural fit to such problems, and provide empirical validation on synthetic and publicly available datasets. The results show that by combining active and transfer learning, we can achieve faster learning with fewer labels on a target domain than by either alone.

KW - active learning

KW - transfer learning

KW - smart home

KW - accelerometers

M3 - Conference Paper

T2 - European Symposium on Artificial Neural Networks

Y2 - 27 April 2016 through 29 April 2016

ER -

Active transfer learning for activity recognition

Abstract

Conference

Research Groups and Themes

Keywords

Access to Document

Handle.net

Fingerprint

Projects

SPHERE (EPSRC IRC)

Cite this