A simple squared-error reformulation for ordinal classification Article Swipe

PDF

Related Concepts

Softmax function Mean squared error Computer science Simple (philosophy) Context (archaeology) Ordinal data Ordinal regression Artificial intelligence Class (philosophy) Pattern recognition (psychology) Artificial neural network Algorithm Machine learning Statistics Mathematics Epistemology Biology Philosophy Paleontology

Christopher Beckham , Christopher Pal ·

YOU? · · 2016 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1612.00775 · OA: W2560046091

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.