Virtual Diagnostic (VD) is a deep learning tool that can be used to pred...
ResNets constrained to be bi-Lipschitz, that is, approximately distance
...
We propose a new model that estimates uncertainty in a single forward pa...
The growth in the number of galaxy images is much faster than the speed ...
'Capsule' models try to explicitly represent the poses of objects, enfor...
We propose a method for training a deterministic deep model that can fin...
We challenge the longstanding assumption that the mean-field approximati...
Evaluation of Bayesian deep learning (BDL) methods is challenging. We of...
Satellite imaging is a critical technology for monitoring and responding...
We use Bayesian convolutional neural networks and a novel generative mod...
We prove that idealised discriminative Bayesian neural networks, capturi...
Measuring uncertainty is a promising technique for detecting adversarial...