CUED Publications database

Sensitivity analysis for predictive uncertainty in Bayesian neural networks

Depeweg, S and Hernández-Lobato, JM and Udluft, S and Runkler, T (2018) Sensitivity analysis for predictive uncertainty in Bayesian neural networks. ESANN 2018 - Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. pp. 279-284.

Full text not available from this repository.

Abstract

© ESANN 2018 - Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. We derive a novel sensitivity analysis of input variables for predictive epistemic and aleatoric uncertainty. We use Bayesian neural networks with latent variables as a model class and illustrate the usefulness of our sensitivity analysis on real-world datasets. Our method increases the interpretability of complex black-box probabilistic models.

Item Type: Article
Uncontrolled Keywords: stat.ML stat.ML
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 13 Dec 2017 20:07
Last Modified: 18 Aug 2020 12:41
DOI: