Gaussian processes are a powerful framework for quantifying uncertainty and for sequential
decision-making but are limited by the requirement of solving linear systems. In general, this …

The linearised Laplace method for estimating model uncertainty has received renewed
attention in the Bayesian deep learning community. The method provides reliable error bars …

Large-scale linear models are ubiquitous throughout machine learning, with contemporary
application as surrogate models for neural network uncertainty quantification; that is, the …

Deep image prior (DIP) was recently introduced as an effective unsupervised approach for
image restoration tasks. DIP represents the image to be recovered as the output of a deep …

The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in
constructing Bayesian neural networks. It is theoretically compelling since it can be seen as …

In X-ray Computed Tomography (CT), projections from many angles are acquired and used
for 3D reconstruction. To make CT suitable for in-line quality control, reducing the number of …

Supervised deep learning (SDL) methodology holds promise for accelerated magnetic
resonance imaging (AMRI) but is hampered by the reliance on extensive training data …

Data-based methods, in particular deep learning methods, have been successfully applied
to solve various inverse problems. In medical imaging, for example in computed tomography …