
Probabilistic Deep Learning with Probabilistic Neural Networks and Deep Probabilistic Models
Probabilistic deep learning is deep learning that accounts for uncertain...
read it

Hybrid Bayesian Neural Networks with Functional Probabilistic Layers
Bayesian neural networks provide a direct and natural way to extend stan...
read it

ZhuSuan: A Library for Bayesian Deep Learning
In this paper we introduce ZhuSuan, a python probabilistic programming l...
read it

DBSN: Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structures
Bayesian neural networks (BNNs) introduce uncertainty estimation to deep...
read it

Functional Space Variational Inference for Uncertainty Estimation in Computer Aided Diagnosis
Deep neural networks have revolutionized medical image analysis and dise...
read it

On the Validity of Bayesian Neural Networks for Uncertainty Estimation
Deep neural networks (DNN) are versatile parametric models utilised succ...
read it

UncertaintyAware Surrogate Model For Oilfield Reservoir Simulation
Deep neural networks have gained increased attention in machine learning...
read it
Bayesian Neural Networks: Essentials
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 dropin 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.
READ FULL TEXT
Comments
There are no comments yet.