Neural networks (NNs) are currently changing the computational paradigm on how to
combine data with mathematical laws in physics and engineering in a profound way …

An in-depth understanding of uncertainty is the first step to making effective decisions under
uncertainty. Machine/deep learning (ML/DL) has been hugely leveraged to solve complex …

With only video-level event labels, this paper targets at the task of weakly-supervised audio-
visual event perception (WS-AVEP), which aims to temporally localize and categorize events …

With the explosive growth of videos, weakly-supervised temporal action localization (WS-
TAL) task has become a promising research direction in pattern analysis and machine …

Traversing terrain with good traction is crucial for achieving fast off-road navigation. Instead
of manually designing costs based on terrain features, existing methods learn terrain …

Uncertainty awareness is crucial to develop reliable machine learning models. In this work,
we propose the Natural Posterior Network (NatPN) for fast and high-quality uncertainty …

Reliable uncertainty estimation has become a crucial requirement for the industrial
deployment of deep learning algorithms, particularly in high-risk applications such as …

In the past couple of years, various approaches to representing and quantifying different
types of predictive uncertainty in machine learning, notably in the setting of classification …

Evidential deep learning, built upon belief theory and subjective logic, offers a principled
and computationally efficient way to turn a deterministic neural network uncertainty-aware …

Abstract Graph Neural Networks (GNNs) are promising surrogates for quantum mechanical
calculations as they establish unprecedented low errors on collections of molecular …