Can Bayesian Neural Networks Explicitly Model Input Uncertainty?

Matias Valdenegro-Toro, Marco Zullich

2025

Abstract

Inputs to machine learning models can have associated noise or uncertainties, but they are often ignored and not modelled. It is unknown if Bayesian Neural Networks and their approximations are able to consider uncertainty in their inputs. In this paper we build a two input Bayesian Neural Network (mean and standard deviation) and evaluate its capabilities for input uncertainty estimation across different methods like Ensembles, MC-Dropout, and Flipout. Our results indicate that only some uncertainty estimation methods for approximate Bayesian NNs can model input uncertainty, in particular Ensembles and Flipout.

Paper Citation

in Harvard Style

Valdenegro-Toro M. and Zullich M. (2025). Can Bayesian Neural Networks Explicitly Model Input Uncertainty?. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 188-199. DOI: 10.5220/0013313300003912

in Bibtex Style

@conference{visapp25,
author={Matias Valdenegro-Toro and Marco Zullich},
title={Can Bayesian Neural Networks Explicitly Model Input Uncertainty?},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={188-199},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013313300003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Can Bayesian Neural Networks Explicitly Model Input Uncertainty?
SN - 978-989-758-728-3
AU - Valdenegro-Toro M.
AU - Zullich M.
PY - 2025
SP - 188
EP - 199
DO - 10.5220/0013313300003912
PB - SciTePress