Calibrating Deep Convolutional Gaussian Processes
Machine Learning
2018-05-29 v1 Machine Learning
Abstract
The wide adoption of Convolutional Neural Networks (CNNs) in applications where decision-making under uncertainty is fundamental, has brought a great deal of attention to the ability of these models to accurately quantify the uncertainty in their predictions. Previous work on combining CNNs with Gaussian processes (GPs) has been developed under the assumption that the predictive probabilities of these models are well-calibrated. In this paper we show that, in fact, current combinations of CNNs and GPs are miscalibrated. We proposes a novel combination that considerably outperforms previous approaches on this aspect, while achieving state-of-the-art performance on image classification tasks.
Cite
@article{arxiv.1805.10522,
title = {Calibrating Deep Convolutional Gaussian Processes},
author = {Gia-Lac Tran and Edwin V. Bonilla and John P. Cunningham and Pietro Michiardi and Maurizio Filippone},
journal= {arXiv preprint arXiv:1805.10522},
year = {2018}
}
Comments
12 pages