Abstract Among Bayesian methods, Monte Carlo dropout provides principled tools for
evaluating the epistemic uncertainty of neural networks. Its popularity recently led to seminal …

We propose a post-hoc computationally lightweight method to quantify predictive uncertainty
in semantic image segmentation. Our approach uses conformal prediction to generate …

Due to the inherent presence of uncertainty in machine learning (ML) systems, the usage of
ML is until now out of scope for many critical (financial) business processes. One such …

We consider how human-centered causal theories and tools from the dynamical systems
literature can be deployed to guide the representation of data when training neural networks …

Machine learning has made tremendous strides in the past decades at producing state-of-
the-art results in safety-critical fields such as self-driving vehicles and medicine. Current …