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

This article reviews applications of Bayesian inference and machine learning (ML) in
nuclear fusion research. Current and next-generation nuclear fusion experiments require …

We show that a single softmax neural net with minimal changes can beat the uncertainty
predictions of Deep Ensembles and other more complex single-forward-pass uncertainty …

Automated driving and vehicle safety systems need object detection. It is important that
object detection be accurate overall and robust to weather and environmental conditions …

Since real-world machine systems are running in non-stationary environments, Continual
Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually …

Rapid advancements in communication technology have made vehicular networks a reality
with numerous applications. However, vehicular network security is still an open research …

A real-time Bangla Sign Language interpreter can enable more than 200 k hearing and
speech-impaired people to the mainstream workforce in Bangladesh. Bangla Sign …

Autonomous vehicles (AVs) are expected to reshape future transportation systems, and
decision making is one of the critical modules toward high-level automated driving. To …