Unimodal Probability Distributions for Deep Ordinal Classification

Christopher Beckham, Christopher Pal
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:411-419, 2017.

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 this Paper

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.} }
Endnote
%0 Conference Paper %T Unimodal Probability Distributions for Deep Ordinal Classification %A Christopher Beckham %A Christopher Pal %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-beckham17a %I PMLR %P 411--419 %U https://proceedings.mlr.press/v70/beckham17a.html %V 70 %X 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.
APA
Beckham, C. & Pal, C.. (2017). Unimodal Probability Distributions for Deep Ordinal Classification. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:411-419 Available from https://proceedings.mlr.press/v70/beckham17a.html.

Related Material