Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue.
Uncertainty quantification is required for many applications, and disentangled aleatoric and …

The quantification of aleatoric and epistemic uncertainty in terms of conditional entropy and
mutual information, respectively, has recently become quite common in machine learning …

Uncertainty quantification of deep neural networks has become an active field of research
and plays a crucial role in various downstream tasks such as active learning. Recent …

Reliable uncertainty from deterministic single-forward pass models is sought after because
conventional methods of uncertainty quantification are computationally expensive. We take …

We provide single-model estimates of aleatoric and epistemic uncertainty for deep neural
networks. To estimate aleatoric uncertainty, we propose Simultaneous Quantile Regression …

Reliable uncertainty from deterministic single-forward pass models is sought after because
conventional methods of uncertainty quantification are computationally expensive. We take …

Quantifying uncertainty is important for actionable predictions in real-world applications. A
crucial part of predictive uncertainty quantification is the estimation of epistemic uncertainty …

A set of novel approaches for estimating epistemic uncertainty in deep neural networks with
a single forward pass has recently emerged as a valid alternative to Bayesian Neural …

High-quality estimates of uncertainty and robustness are crucial for numerous real-world
applications, especially for deep learning which underlies many deployed ML systems. The …

While deep neural networks have become the go-to approach in computer vision, the vast
majority of these models fail to properly capture the uncertainty inherent in their predictions …