Deep kernel learning for integral measurements

09/04/2019

∙

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.

READ FULL TEXT

Deep kernel learning for integral measurements

Improved Asymptotics for Zeros of Kernel Estimates via a Reformulation of the Leadbetter-Cryer Integral

Fixed Integral Neural Networks

A projected Nesterov-Kaczmarz approach to stellar population-kinematic distribution reconstruction in Extragalactic Archaeology

Separability of the kernel function in an integral formulation for anisotropic radiative transfer equation

Full-pulse Tomographic Reconstruction with Deep Neural Networks

Machine Learning with the Sugeno Integral: The Case of Binary Classification

Parallel and Limited Data Voice Conversion Using Stochastic Variational Deep Kernel Learning

Deep kernel learning for integral measurements

Related Research

Improved Asymptotics for Zeros of Kernel Estimates via a Reformulation of the Leadbetter-Cryer Integral

Fixed Integral Neural Networks

A projected Nesterov-Kaczmarz approach to stellar population-kinematic distribution reconstruction in Extragalactic Archaeology

Separability of the kernel function in an integral formulation for anisotropic radiative transfer equation

Full-pulse Tomographic Reconstruction with Deep Neural Networks

Machine Learning with the Sugeno Integral: The Case of Binary Classification

Parallel and Limited Data Voice Conversion Using Stochastic Variational Deep Kernel Learning