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 …

With a mortality rate of 5.4 million lives worldwide every year and a healthcare cost of more
than 16 billion dollars in the USA alone, sepsis is one of the leading causes of hospital …

Multimodal spatiotemporal data (MST) consists of multiple simultaneous spatiotemporal
modalities that interact with each other in a dynamic manner. Due to the complexity of MST …

We propose a new model of Variational Autoencoder (VAE) for Anomaly Detection (AD) with
improved modeling power. More precisely, we introduce a VAE model with a Gaussian …

In real world datasets of aerial images, the objects of interest are often missing, hard to
annotate and of varying aspects. The framework of unsupervised Anomaly Detection (AD) is …

Complex multivariate time series arise in many fields, ranging from computer vision to
robotics or medicine. Often we are interested in the independent underlying factors that give …

Variational auto-encoders have proven to capture complicated data distributions and useful
latent representations, while advances in meta-learning have made it possible to extract …

Deep learning has positioned itself as one of the most promising directions of machine
learning in recent years. Nonetheless, deep neural networks have many shortcomings, for …

The irruption of the smartphone into everyone's life and the ease with which we digitise or
record any data supposed an explosion of quantities of data. Smartphones, equipped with …