Bayesian Neural Networks: An Introduction and Survey
This is an incremental survey article for researchers in machine learning interested in uncertainty quantification.
The paper introduces Bayesian Neural Networks (BNNs) to address the inability of frequentist neural networks to reason about uncertainty in predictions, surveying existing methods and comparing approximate inference techniques to identify areas for future improvement.
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 of computer vision, speech recognition and natural language processing. Despite their success, they are often implemented in a frequentist scheme, meaning they are unable to reason about uncertainty in their predictions. This article introduces Bayesian Neural Networks (BNNs) and the seminal research regarding their implementation. Different approximate inference methods are compared, and used to highlight where future research can improve on current methods.