On the Validity of Bayesian Neural Networks for Uncertainty Estimation
|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 networks; Uncertainty quantification; Robustness||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
If you are a publisher or author and have copyright concerns for any item, please email firstname.lastname@example.org and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.