Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of
challenging problems. However, since deep learning methods operate as black boxes, the …

Continual learning (CL) aims to enable information systems to learn from a continuous data
stream across time. However, it is difficult for existing deep learning architectures to learn a …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

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 …

The posterior over Bayesian neural network (BNN) parameters is extremely high-
dimensional and non-convex. For computational reasons, researchers approximate this …

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

Federated learning faces huge challenges from model overfitting due to the lack of data and
statistical diversity among clients. To address these challenges, this paper proposes a novel …

Offline Reinforcement Learning promises to learn effective policies from previously-
collected, static datasets without the need for exploration. However, existing Q-learning and …

During the past five years the Bayesian deep learning community has developed
increasingly accurate and efficient approximate inference procedures that allow for …

Photoacoustic imaging (PAI) is a promising emerging imaging modality that enables
spatially resolved imaging of optical tissue properties up to several centimeters deep in …