Deep kernel learning for integral measurements

TL;DR

This paper introduces a deep kernel learning method tailored for problems involving line integral measurements, demonstrating its effectiveness in computed tomography reconstruction tasks.

Contribution

It presents a novel approach combining neural networks with Gaussian processes specifically for integral measurement data.

Findings

Effective in computed tomography reconstruction

Improves modeling of complex functions from integral data

Demonstrates feasibility of deep kernel learning for integral measurements

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.