Go to  Advanced Search

Priors for Bayesian Neural Networks

Show full item record

Files in this item

Files Size Format Description   View
ubc_2001-0583.pdf 2.868Mb Adobe Portable Document Format   View/Open
Title: Priors for Bayesian Neural Networks
Author: Robinson, Mark
Degree: Master of Science - MSc
Program: Statistics
Copyright Date: 2001
Issue Date: 2009-08-06
Series/Report no. UBC Retrospective Theses Digitization Project [http://www.library.ubc.ca/archives/retro_theses/]
Abstract: In recent years, Neural Networks (NN) have become a popular data-analytic tool in Statistics, Computer Science and many other fields. NNs can be used as universal approximators, that is, a tool for regressing a dependent variable on a possibly complicated function of the explanatory variables. The NN parameters, unfortunately, are notoriously hard to interpret. Under the Bayesian view, we propose and discuss prior distributions for some of the network parameters which encourage parsimony and reduce overfit, by eliminating redundancy, promoting orthogonality, linearity or additivity. Thus we consider more senses of parsimony than are discussed in the existing literature. We investigate the predictive performance of networks fit under these various priors. The Deviance Information Criterion (DIC) is briefly explored as a model selection criterion.
Affiliation: Science, Faculty of
URI: http://hdl.handle.net/2429/11911
Scholarly Level: Graduate

This item appears in the following Collection(s)

Show full item record

UBC Library
1961 East Mall
Vancouver, B.C.
Canada V6T 1Z1
Tel: 604-822-6375
Fax: 604-822-3893