While the choice of prior is one of the most critical parts of the Bayesian inference workflow,
recent Bayesian deep learning models have often fallen back on vague priors, such as …

Federated Learning (FL) aims to train a global inference model from remotely distributed
clients, gaining popularity due to its benefit of improving data privacy. However, traditional …

We introduce a deterministic variational formulation for training Bayesian last layer neural
networks. This yields a sampling-free, single-pass model and loss that effectively improves …

Uncertainty quantification is an important task in machine learning-a task in which standard
neural networks (NNs) have traditionally not excelled. This can be a limitation for safety …

Physics-informed extreme learning machine (PIELM) has recently received significant
attention as a rapid version of physics-informed neural network (PINN) for solving partial …

The Laplace approximation provides a closed-form model selection objective for neural
networks (NN). Online variants, which optimise NN parameters jointly with hyperparameters …

The capability to replicate the predictions by machine learning (ML) or artificial intelligence
(AI) models and the results in scientific workflows that incorporate such ML/AI predictions is …

Assessing the predictive uncertainty of deep neural networks is crucial for safety-related
applications of deep learning. Although Bayesian deep learning offers a principled …

Traffic fatalities remain among the leading death causes worldwide. To reduce this figure,
car safety is listed as one of the most important factors. To actively support human drivers, it …

Well-calibrated probabilistic regression models are a crucial learning component in robotics
applications as datasets grow rapidly and tasks become more complex. Unfortunately …