Show simple item record

dc.contributor.authorWang, Hao
dc.contributor.authorHe, Hao
dc.contributor.authorZhao, Mingmin
dc.contributor.authorJaakkola, Tommi S
dc.contributor.authorKatabi, Dina
dc.date.accessioned2021-01-11T19:03:57Z
dc.date.available2021-01-11T19:03:57Z
dc.date.issued2019-01
dc.identifier.isbn978-1-57735-809-1
dc.identifier.issn2374-3468
dc.identifier.urihttps://hdl.handle.net/1721.1/129372
dc.description.abstractWe consider the problem of inferring the values of an arbitrary set of variables (e.g., risk of diseases) given other observed variables (e.g., symptoms and diagnosed diseases) and high-dimensional signals (e.g., MRI images or EEG). This is a common problem in healthcare since variables of interest often differ for different patients. Existing methods including Bayesian networks and structured prediction either do not incorporate high-dimensional signals or fail to model conditional dependencies among variables. To address these issues, we propose bidirectional inference networks (BIN), which stich together multiple probabilistic neural networks, each modeling a conditional dependency. Predictions are then made via iteratively updating variables using backpropagation (BP) to maximize corresponding posterior probability. Furthermore, we extend BIN to composite BIN (CBIN), which involves the iterative prediction process in the training stage and improves both accuracy and computational efficiency by adaptively smoothing the optimization landscape. Experiments on synthetic and real-world datasets (a sleep study and a dermatology dataset) show that CBIN is a single model that can achieve state-of-the-art performance and obtain better accuracy in most inference tasks than multiple models each specifically trained for a different task.en_US
dc.language.isoen
dc.publisherAssociation for the Advancement of Artificial Intelligence (AAAI)en_US
dc.relation.isversionof10.1609/AAAI.V33I01.3301766en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleBidirectional Inference Networks:A Class of Deep Bayesian Networks for Health Profilingen_US
dc.typeArticleen_US
dc.identifier.citationWang, Hao et al. “Bidirectional Inference Networks:A Class of Deep Bayesian Networks for Health Profiling.” Proceedings of the AAAI Conference on Artificial Intelligence, 33, 1 (January 2019) © 2019 The Author(s)en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.relation.journalProceedings of the AAAI Conference on Artificial Intelligenceen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2020-12-21T16:18:36Z
dspace.orderedauthorsWang, H; Mao, C; He, H; Zhao, M; Jaakkola, TS; Katabi, Den_US
dspace.date.submission2020-12-21T16:18:39Z
mit.journal.volume33en_US
mit.journal.issue1en_US
mit.licenseOPEN_ACCESS_POLICY


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record