Uncertainty quantification in neural network classifiers -- a local linear approach
Abstract
Classifiers based on neural networks (NN) often lack a measure of uncertainty in the predicted class. We propose a method to estimate the probability mass function (PMF) of the different classes, as well as the covariance of the estimated PMF. First, a local linear approach is used during the training phase to recursively compute the covariance of the parameters in the NN. Secondly, in the classification phase another local linear approach is used to propagate the covariance of the learned NN parameters to the uncertainty in the output of the last layer of the NN. This allows for an efficient Monte Carlo (MC) approach for: (i) estimating the PMF; (ii) calculating the covariance of the estimated PMF; and (iii) proper risk assessment and fusion of multiple classifiers. Two classical image classification tasks, i.e., MNIST, and CFAR10, are used to demonstrate the efficiency the proposed method.
Cite
@article{arxiv.2303.07114,
title = {Uncertainty quantification in neural network classifiers -- a local linear approach},
author = {Magnus Malmström and Isaac Skog and Daniel Axehill and Fredrik Gustafsson},
journal= {arXiv preprint arXiv:2303.07114},
year = {2024}
}
Comments
10 pages, 2 figures. Submitted to Elsevier for possible publication