Mitros, John (Ioannis)John (Ioannis)MitrosMacNamee, BrianBrianMacNamee2021-05-262021-05-262019 the A2019-12-06http://hdl.handle.net/10197/12203The 27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2019) Galway, Ireland, 5-6 December 2019Deep 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.enBayesian neural networksUncertainty quantificationRobustnessConference Publication2021-01-2415/CDA/352012/RC/2289https://creativecommons.org/licenses/by/3.0/ie/