Wang, P., Bouaynaya, N.C., Mihaylova, L. orcid.org/0000-0001-5856-2223 et al. (3 more authors) (2020) Bayesian neural networks uncertainty quantification with cubature rules. In: Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN). 2020 International Joint Conference on Neural Networks (IJCNN), 19-24 Jul 2020, Glasgow, United Kingdom. IEEE , pp. 1-7. ISBN 9781728169279
Abstract
Bayesian neural networks are powerful inference methods by accounting for randomness in the data and the network model. Uncertainty quantification at the output of neural networks is critical, especially for applications such as autonomous driving and hazardous weather forecasting. However, approaches for theoretical analysis of Bayesian neural networks remain limited. This paper makes a step forward towards mathematical quantification of uncertainty in neural network models and proposes a cubature-rule-based computationally-efficient uncertainty quantification approach that captures layer-wise uncertainties of Bayesian neural networks. The proposed approach approximates the first two moments of the posterior distribution of the parameters by propagating cubature points across the network nonlinearities. Simulation results show that the proposed approach can achieve more diverse layer-wise uncertainty quantification results of neural networks with a fast convergence rate.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. Reproduced in accordance with the publisher's self-archiving policy. |
Keywords: | Bayesian neural networks; uncertainty quantification; cubature rules; variational inference; Bayesian rules |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) |
Funding Information: | Funder Grant number Engineering and Physical Science Research Council EP/T013265/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 29 Apr 2020 08:25 |
Last Modified: | 28 Sep 2021 00:38 |
Status: | Published |
Publisher: | IEEE |
Refereed: | Yes |
Identification Number: | 10.1109/IJCNN48605.2020.9207214 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:160037 |