Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
This is an incremental tutorial aimed at deep learning users seeking to apply Bayesian methods for uncertainty quantification.
The tutorial addresses the challenge of quantifying uncertainty in deep learning predictions by introducing Bayesian Neural Networks, providing a comprehensive toolset for their design, implementation, and evaluation.
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 uncertainty associated with their predictions is often challenging to quantify. Bayesian statistics offer a formalism to understand and quantify the uncertainty associated with deep neural network predictions. This tutorial provides an overview of the relevant literature and a complete toolset to design, implement, train, use and evaluate Bayesian Neural Networks, i.e. Stochastic Artificial Neural Networks trained using Bayesian methods.