Implicit Weight Uncertainty in Neural Networks

File Description SizeFormat 
1711.01297v1.pdfPublished version359.24 kBAdobe PDFView/Open
Title: Implicit Weight Uncertainty in Neural Networks
Authors: Pawlowski, N
Rajchl, M
Glocker, B
Item Type: Working Paper
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.
Issue Date: 31-Dec-2017
URI: http://hdl.handle.net/10044/1/54603
Copyright Statement: © The Authors
Sponsor/Funder: Microsoft Reseach
Keywords: stat.ML
cs.LG
Notes: Submitted to Bayesian Deep Learning Workshop at NIPS 2017
Appears in Collections:Faculty of Engineering
Computing
Department of Medicine
Faculty of Medicine



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons