Conference item icon

Conference item

Interpreting lion behaviour with nonparametric probabilistic programs

Abstract:

We consider the problem of unsupervised learning of meaningful behavioural segments of high-dimensional time-series observations, collected from a pride of African lions. We demonstrate, by way of probabilistic programming, a methodology which allows for quick iteration over models and Bayesian inferences, which enables us to learn meaningful behavioural segments. We introduce a new Bayesian nonparametric (BNP) state-space model, which extends the HDP-HMM with an explicit BNP treatment of dur...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
Societies, Other & Subsidiary Companies
Department:
Kellogg College
Oxford college:
Kellogg College
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Zoology
Role:
Author
Expand authors...
More from this funder
Funding agency for:
Dhir, N
Grant:
EP/G036861/1
Publisher:
Association for Uncertainty in Artificial Intelligence Publisher's website
Journal:
33rd Conference on Uncertainty in Artificial Intelligence, Sydney, Australia, August 1-15, 2017 Journal website
Host title:
33rd Conference on Uncertainty in Artificial Intelligence, Sydney, Australia, August 1-15, 2017
Publication date:
2017-01-01
Acceptance date:
2017-06-12
Source identifiers:
708826
Pubs id:
pubs:708826
UUID:
uuid:b90d0eeb-8e5f-4571-ba4b-500cc8d62936
Local pid:
pubs:708826
Deposit date:
2017-07-20

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP