Notes on the Behavior of MC Dropout
Machine Learning
2021-07-14 v2 Machine Learning
Abstract
Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness. However the quality of the uncertainty estimated through this method varies and choices in architecture design and in training procedures have to be carefully considered and tested to obtain satisfactory results. In this paper we present a study offering a different point of view on the behavior of Monte-Carlo dropout, which enables us to observe a few interesting properties of the technique to keep in mind when considering its use for uncertainty estimation.
Cite
@article{arxiv.2008.02627,
title = {Notes on the Behavior of MC Dropout},
author = {Francesco Verdoja and Ville Kyrki},
journal= {arXiv preprint arXiv:2008.02627},
year = {2021}
}
Comments
Presented at the ICML 2021 Workshop on "Uncertainty and Robustness in Deep Learning"