Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of
challenging problems. However, since deep learning methods operate as black boxes, the …

While perception tasks such as visual object recognition and text understanding play an
important role in human intelligence, subsequent tasks that involve inference, reasoning …

During the past five years the Bayesian deep learning community has developed
increasingly accurate and efficient approximate inference procedures that allow for …

Abstract Neural Networks (NNs) have provided state-of-the-art results for many challenging
machine learning tasks such as detection, regression and classification across the domains …

Stochastic variational inference for Bayesian deep neural network (DNN) requires specifying
priors and approximate posterior distributions over neural network weights. Specifying …

The Bayesian treatment of neural networks dictates that a prior distribution is specified over
their weight and bias parameters. This poses a challenge because modern neural networks …

This paper describes and discusses Bayesian Neural Network (BNN). The paper showcases
a few different applications of them for classification and regression problems. BNNs are …

The key distinguishing property of a Bayesian approach is marginalization instead of
optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for …

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 …

We show that training a deep network using batch normalization is equivalent to
approximate inference in Bayesian models. We further demonstrate that this finding allows …