Unimodal Probability Distributions for Deep Ordinal Classification

Christopher Beckham; Christopher Pal

ICML 2017poster103 citations

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.

BibTeX

@InProceedings{pmlr-v70-beckham17a,
  title = 	 {Unimodal Probability Distributions for Deep Ordinal Classification},
  author =       {Christopher Beckham and Christopher Pal},
  booktitle = 	 {Proceedings of the 34th International Conference on Machine Learning},
  pages = 	 {411--419},
  year = 	 {2017},
  editor = 	 {Precup, Doina and Teh, Yee Whye},
  volume = 	 {70},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {06--11 Aug},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v70/beckham17a/beckham17a.pdf},
  url = 	 {https://proceedings.mlr.press/v70/beckham17a.html},
  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.}
}