Show simple item record

dc.contributor.authorJanz, Daviden
dc.contributor.authorWesthuizen, Jos van deren
dc.contributor.authorHernández-Lobato, José Miguelen
dc.date.accessioned2018-07-09T12:41:02Z
dc.date.available2018-07-09T12:41:02Z
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/277916
dc.description.abstractDeep learning techniques have been hugely successful for traditional supervised and unsupervised machine learning problems. In large part, these techniques solve continuous optimization problems. Recently however, discrete generative deep learning models have been successfully used to efficiently search high-dimensional discrete spaces. These methods work by representing discrete objects as sequences, for which powerful sequence-based deep models can be employed. Unfortunately, these techniques are significantly hindered by the fact that these generative models often produce invalid sequences. As a step towards solving this problem, we propose to learn a deep recurrent validator model. Given a partial sequence, our model learns the probability of that sequence occurring as the beginning of a full valid sequence. Thus this identifies valid versus invalid sequences and crucially it also provides insight about how individual sequence elements influence the validity of discrete objects. To learn this model we propose an approach inspired by seminal work in Bayesian active learning. On a synthetic dataset, we demonstrate the ability of our model to distinguish valid and invalid sequences. We believe this is a key step toward learning generative models that faithfully produce valid discrete objects.
dc.publisherOpenReview
dc.subjectstat.MLen
dc.subjectstat.MLen
dc.subjectcs.LGen
dc.titleActively Learning what makes a Discrete Sequence Validen
dc.typeConference Object
dc.identifier.doi10.17863/CAM.25251
dcterms.dateAccepted2018-01-29en
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2018-01-29en
rioxxterms.typeConference Paper/Proceeding/Abstracten


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record