Conference item icon

Conference item

Concrete dropout

Abstract:

Dropout is used as a practical tool to obtain uncertainty estimates in large vision models and reinforcement learning (RL) tasks. But to obtain well-calibrated uncertainty estimates, a grid-search over the dropout probabilities is necessary— a prohibitive operation with large models, and an impossible one with RL. We propose a new dropout variant which gives improved performance and better calibrated uncertainties. Relying on recent developments in Bayesian deep learning, we use a continuous ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted manuscript

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Computer Science
Role:
Author
Publisher:
NIPS Foundation Publisher's website
Publication date:
2018-07-01
Acceptance date:
2017-09-04
Pubs id:
pubs:746866
URN:
uri:2779c391-6a38-4c70-be60-7b0c8c88a1a2
UUID:
uuid:2779c391-6a38-4c70-be60-7b0c8c88a1a2
Local pid:
pubs:746866

Terms of use


Metrics


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