Implicit Weight Uncertainty in Neural Networks (2017-11-03T00:00:00.000000Z)

TL;DR

The method, Bayes by Hypernet, is able to model a richer variational distribution than previous methods and achieves comparable predictive performance on the MNIST classification task while providing higher predictive uncertainties compared to MC-Dropout and regular maximum likelihood training.

Abstract

We interpret HyperNetworks within the framework of variational inference within implicit distributions. Our method, Bayes by Hypernet, is able to model a richer variational distribution than previous methods. Experiments show that it achieves comparable predictive performance on the MNIST classification task while providing higher predictive uncertainties compared to MC-Dropout and regular maximum likelihood training.

Authors

Ben Glocker

10 papers

Nick Pawlowski

4 papers

Martin Rajchl

3 papers

Implicit Weight Uncertainty in Neural Networks

TL;DR

Abstract

Authors

References16 items

Bayesian Hypernetworks

SMASH: One-Shot Model Architecture Search through HyperNetworks

On Calibration of Modern Neural Networks

Multiplicative Normalizing Flows for Variational Bayesian Neural Networks

Deep and Hierarchical Implicit Models

Variational Inference using Implicit Distributions

Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

HyperNetworks

Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks

Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference

Weight Uncertainty in Neural Networks

Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks

Adam: A Method for Stochastic Optimization

Conditional Generative Adversarial Nets

GENERATIVE ADVERSARIAL NETS

Deep Learning

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names