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 …

Popular approaches for quantifying predictive uncertainty in deep neural networks often
involve distributions over weights or multiple models, for instance via Markov Chain …

Popular approaches for quantifying predictive uncertainty in deep neural networks often
involve a set of weights or models, for instance via ensembling or Monte Carlo Dropout …

Efficiently executing inference tasks of deep neural networks on devices with limited
resources poses a significant load in IoT systems. To alleviate the load, one innovative …

Maximum likelihood (ML) learning for energy‐based models (EBMs) is challenging, partly
due to nonconvergence of Markov chain Monte Carlo. Several variations of ML learning …

Optical character recognition (OCR) has proved a powerful tool for the digital analysis of
printed historical documents. However, its ability to localize and identify individual glyphs is …

This paper introduces a novel family of deep dynamical models designed to represent
continuous-time sequence data. This family of models generates each data point in the time …

Classification tasks present challenges due to class imbalances and evolving data
distributions. Addressing these issues requires a robust method to handle imbalances while …

Though pre-trained language models achieve notable success in many applications, it's
usually controversial for over-confident predictions. Specifically, the in-distribution (ID) …

Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep
neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection …