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 …

Abstract Variational Autoencoders (VAEs) are powerful generative models that merge
elements from statistics and information theory with the flexibility offered by deep neural …

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 …