In this paper, we explore ordinal classification (in the context of deep neural networks) through a simple modification of the squared error loss which not only allows it to not only be sensitive to class ordering, but also allows the possibility of having a discrete probability distribution over the classes. Our formulation is based on the use of a softmax hidden layer, which has received relatively little attention in the literature. We empirically evaluate its performance on the Kaggle diabetic retinopathy dataset, an ordinal and high-resolution dataset and show that it outperforms all of the baselines employed.
@article{arxiv.1612.00775,
title = {A simple squared-error reformulation for ordinal classification},
author = {Christopher Beckham and Christopher Pal},
journal= {arXiv preprint arXiv:1612.00775},
year = {2017}
}
Comments
v1: Camera-ready abstract for NIPS for Health Workshop (2016) v2: Clean-up of some sections, added appendix section where we briefly explore optimisation of quadratic weighted kappa (QWK)