Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. MIT Open Access Articles
  3. MIT Open Access Articles
  4. Bidirectional Inference Networks:A Class of Deep Bayesian Networks for Health Profiling

Bidirectional Inference Networks:A Class of Deep Bayesian Networks for Health Profiling

Thumbnail Image
Download
Name

1902.02037.pdf

Description
Accepted version
Size

990.74 KB

Format

Adobe PDF

Checksum (MD5)

ce5cdc3b455cfddcd5c4e7d7c9ff169d

sword-2020-12-21T16:18:36.original.xml (130 B)
Original SWORD entry document
Author(s)
Wang, Hao
•
He, Hao
•
Zhao, Mingmin
•
Jaakkola, Tommi S
•
Katabi, Dina
Date Issued
January 2019
Journal
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Citation
Wang, 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)
Version
Author's final manuscript
Abstract
We 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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
http://creativecommons.org/licenses/by-nc-sa/4.0/
Persistent DSpace Link
https://hdl.handle.net/1721.1/129372
DOI of Published Version
https://doi.org/10.1609/AAAI.V33I01.3301766
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.