Deep kernel learning for integral measurements
Machine Learning
2019-09-05 v1 Machine Learning
Abstract
Deep kernel learning refers to a Gaussian process that incorporates neural networks to improve the modelling of complex functions. We present a method that makes this approach feasible for problems where the data consists of line integral measurements of the target function. The performance is illustrated on computed tomography reconstruction examples.
Keywords
Cite
@article{arxiv.1909.01844,
title = {Deep kernel learning for integral measurements},
author = {Carl Jidling and Johannes Hendriks and Thomas B. Schön and Adrian Wills},
journal= {arXiv preprint arXiv:1909.01844},
year = {2019}
}