A Caltech Library Service

Bayesian Model Comparison and Backprop Nets

MacKay, David J. C. (1992) Bayesian Model Comparison and Backprop Nets. In: Advances in Neural Information Processing Systems 4 (NIPS 1991). Advances in Neural Information Processing Systems. No.4. Morgan Kaufmann , San Mateo, CA, pp. 839-846. ISBN 1-55860-222-4.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


The Bayesian model comparison framework is reviewed, and the Bayesian Occam's razor is explained. This framework can be applied to feedforward networks, making possible (1) objective comparisons between solutions using alternative network architectures; (2) objective choice of magnitude and type of weight decay terms; (3) quantified estimates of the error bars on network parameters and on network output. The framework also generates a measure of the effective number of parameters determined by the data. The relationship of Bayesian model comparison to recent work on prediction of generalisation ability (Guyon et al., 1992, Moody, 1992) is discussed.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Additional Information:© 1992 Morgan Kaufmann. This work was supported by studentships from Caltech and SERC, UK.
Funding AgencyGrant Number
Science and Engineering Research Council (SERC)UNSPECIFIED
Series Name:Advances in Neural Information Processing Systems
Issue or Number:4
Record Number:CaltechAUTHORS:20160121-165028464
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:63860
Deposited On:22 Jan 2016 22:43
Last Modified:03 Oct 2019 09:32

Repository Staff Only: item control page