Driven by recent advances in Artificial Intelligence (AI) and Computer Vision (CV), the
implementation of AI systems in the medical domain increased correspondingly. This is …

While the choice of prior is one of the most critical parts of the Bayesian inference workflow,
recent Bayesian deep learning models have often fallen back on vague priors, such as …

Incrementally learning new information from a non-stationary stream of data, referred to as
'continual learning', is a key feature of natural intelligence, but a challenging problem for …

Over the last decade, neural networks have reached almost every field of science and
become a crucial part of various real world applications. Due to the increasing spread …

Bayesian formulations of deep learning have been shown to have compelling theoretical
properties and offer practical functional benefits, such as improved predictive uncertainty …

Bayesian neural networks (BNN) and deep ensembles are principled approaches to
estimate the predictive uncertainty of a deep learning model. However their practicality in …

Abstract The generalized Gauss-Newton (GGN) approximation is often used to make
practical Bayesian deep learning approaches scalable by replacing a second order …

Marginal-likelihood based model-selection, even though promising, is rarely used in deep
learning due to estimation difficulties. Instead, most approaches rely on validation data …

We explore the link between deep ensembles and Gaussian processes (GPs) through the
lens of the Neural Tangent Kernel (NTK): a recent development in understanding the …

Abstract The Neural Tangent Kernel (NTK), defined as the outer product of the neural
network (NN) Jacobians, has emerged as a central object of study in deep learning. In the …