Bayesian Model Comparison and Backprop Nets
Abstract
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 gen(cid:173) erates a measure of the effective number of parameters determined by the data. The relationship of Bayesian model comparison to recent work on pre(cid:173) diction of generalisation ability (Guyon et al., 1992, Moody, 1992) is dis(cid:173) cussed.
Cite
Text
MacKay. "Bayesian Model Comparison and Backprop Nets." Neural Information Processing Systems, 1991.Markdown
[MacKay. "Bayesian Model Comparison and Backprop Nets." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/mackay1991neurips-bayesian/)BibTeX
@inproceedings{mackay1991neurips-bayesian,
title = {{Bayesian Model Comparison and Backprop Nets}},
author = {MacKay, David J. C.},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {839-846},
url = {https://mlanthology.org/neurips/1991/mackay1991neurips-bayesian/}
}