On the Validity of Bayesian Neural Networks for Uncertainty Estimation

Files in This Item:
File Description SizeFormat 
aics_15.pdf851.2 kBAdobe PDFDownload
Title: On the Validity of Bayesian Neural Networks for Uncertainty Estimation
Authors: Mitros, John (Ioannis)MacNamee, Brian
Permanent link: http://hdl.handle.net/10197/12203
Date: 6-Dec-2019
Online since: 2021-05-26T10:41:38Z
Abstract: Deep neural networks (DNN) are versatile parametric models utilised successfully in a diverse number of tasks and domains. However, they have limitations—particularly from their lack of robustness and over-sensitivity to out of distribution samples. Bayesian Neural Networks, due to their formulation under the Bayesian framework, provide a principled approach to building neural networks that address these limitations. This work provides an empirical study evaluating and comparing Bayesian Neural Networks to their equivalent point estimate Deep Neural Networks to quantify the predictive uncertainty induced by their parameters, as well as their performance in view of uncertainty. Specifically, we evaluated and compared three point estimate deep neural networks against their alternative comparable Bayesian neural network utilising well-known benchmark image classification datasets.
Funding Details: Science Foundation Ireland
Type of material: Conference Publication
Publisher: CEUR Workshop Proceedings
Series/Report no.: CEUR Workshop Proceedings; 2563
Copyright (published version): 2019 the Authors
Keywords: Bayesian neural networksUncertainty quantificationRobustness
Other versions: http://ceur-ws.org/Vol-2563/
Language: en
Status of Item: Peer reviewed
Is part of: Curry, E., Keane, M.T., Ojo, A., Salwala, D. (eds.). Proceedings for the 27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science
Conference Details: The 27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2019) Galway, Ireland, 5-6 December 2019
This item is made available under a Creative Commons License: https://creativecommons.org/licenses/by/3.0/ie/
Appears in Collections:Computer Science Research Collection
Insight Research Collection

Show full item record

Page view(s)

56
Last Week
3
Last month
checked on Jun 15, 2021

Download(s)

5
checked on Jun 15, 2021

Google ScholarTM

Check


If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.