Unimodal probability distributions for deep ordinal classification
Machine Learning
2017-06-23 v2
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.
Keywords
Cite
@article{arxiv.1705.05278,
title = {Unimodal probability distributions for deep ordinal classification},
author = {Christopher Beckham and Christopher Pal},
journal= {arXiv preprint arXiv:1705.05278},
year = {2017}
}
Comments
Accepted for publication for ICML2017. This is the camera-ready version