Show simple item record

dc.contributor.authorGhahramani, Zoubinen
dc.contributor.authorGal, Yen
dc.contributor.authorIslam, Ren
dc.date.accessioned2017-11-27T16:59:53Z
dc.date.available2017-11-27T16:59:53Z
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/269735
dc.description.abstractEven though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data. Recent advances in deep learning, on the other hand, are notorious for their dependence on large amounts of data. Second, many AL acquisition functions rely on model uncertainty, yet deep learning methods rarely represent such model uncertainty. In this paper we combine recent advances in Bayesian deep learning into the active learning framework in a practical way. We develop an active learning framework for high dimensional data, a task which has been extremely challenging so far, with very sparse existing literature. Taking advantage of specialised models such as Bayesian convolutional neural networks, we demonstrate our active learning techniques with image data, obtaining a significant improvement on existing active learning approaches. We demonstrate this on both the MNIST dataset, as well as for skin cancer diagnosis from lesion images (ISIC2016 task).
dc.description.sponsorshipAlan Turing Institute Grant EP/N510129/1 EPSRC Grant EP/N014162/1 Qualcomm
dc.publisherPMLR
dc.titleDeep Bayesian Active Learning with Image Dataen
dc.typeConference Object
prism.endingPage1192
prism.publicationNameProceedings of Machine Learning Researchen
prism.startingPage1183
prism.volume70en
dc.identifier.doi10.17863/CAM.11070
dcterms.dateAccepted2017-05-14en
rioxxterms.versionVoR*
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2017-05-14en
dc.contributor.orcidGhahramani, Zoubin [0000-0002-7464-6475]
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.conference-nameICML 2017en
pubs.conference-start-date2017-08-06en
cam.orpheus.successThu Nov 05 11:58:25 GMT 2020 - The item has an open VoR version.*
rioxxterms.freetoread.startdate2100-01-01


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record