Bayesian Neural Networks: Essentials

TL;DR

Bayesian neural networks incorporate probabilistic layers to model uncertainty, but their complexity and redundancy in deep architectures pose challenges, which can be mitigated by hybrid approaches with fewer probabilistic layers.

Contribution

This paper explains the essentials of Bayesian neural networks, including inference and priors, and discusses practical hybrid models with fewer probabilistic layers.

Findings

Hybrid Bayesian neural networks reduce computational costs.

Probabilistic layers can be integrated as drop-in replacements.

TensorFlow Probability APIs facilitate implementation.

Abstract

Bayesian neural networks utilize probabilistic layers that capture uncertainty over weights and activations, and are trained using Bayesian inference. Since these probabilistic layers are designed to be drop-in replacement of their deterministic counter parts, Bayesian neural networks provide a direct and natural way to extend conventional deep neural networks to support probabilistic deep learning. However, it is nontrivial to understand, design and train Bayesian neural networks due to their complexities. We discuss the essentials of Bayesian neural networks including duality (deep neural networks, probabilistic models), approximate Bayesian inference, Bayesian priors, Bayesian posteriors, and deep variational learning. We use TensorFlow Probability APIs and code examples for illustration. The main problem with Bayesian neural networks is that the architecture of deep neural networks makes it quite redundant, and costly, to account for uncertainty for a large number of successive layers. Hybrid Bayesian neural networks, which use few probabilistic layers judicially positioned in the networks, provide a practical solution.