Bayesian Neural Networks: An Introduction and Survey

TL;DR

This paper introduces Bayesian Neural Networks, compares various approximate inference methods, and discusses future research directions to improve uncertainty quantification in neural networks.

Contribution

It provides an overview of BNNs, compares different inference techniques, and highlights areas for future research to enhance uncertainty modeling.

Findings

Different approximate inference methods are compared.

Highlights where current methods can be improved.

Provides foundational understanding of BNN implementation.

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 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.