Implicit Weight Uncertainty in Neural Networks

11/03/2017

∙

by   Nick Pawlowski, et al.

∙

0

∙

share

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.