Unimodal Probability Distributions for Deep Ordinal Classification
Abstract
Probability distributions produced by the cross-entropy loss for ordinal classification problems can possess undesired properties. We propose a straightforward technique to constrain discrete ordinal probability distributions to be unimodal via the use of the Poisson and binomial probability distributions. We evaluate this approach in the context of deep learning on two large ordinal image datasets, obtaining promising results.
Cite
Text
Beckham and Pal. "Unimodal Probability Distributions for Deep Ordinal Classification." International Conference on Machine Learning, 2017.Markdown
[Beckham and Pal. "Unimodal Probability Distributions for Deep Ordinal Classification." International Conference on Machine Learning, 2017.](https://mlanthology.org/icml/2017/beckham2017icml-unimodal/)BibTeX
@inproceedings{beckham2017icml-unimodal,
title = {{Unimodal Probability Distributions for Deep Ordinal Classification}},
author = {Beckham, Christopher and Pal, Christopher},
booktitle = {International Conference on Machine Learning},
year = {2017},
pages = {411-419},
volume = {70},
url = {https://mlanthology.org/icml/2017/beckham2017icml-unimodal/}
}