Bayesian Backpropagation Over I-O Functions Rather Than Weights

David H. Wolpert

Working Papers from Santa Fe Institute

Abstract: The conventional Bayesian justification for backprop is that it finds the MAP weight vector. As this paper shows, to find the MAP i-o function instead, one must add a correction term to backprop. That term biases one towards i-o functions with small description lengths, and in particular favors (some kinds of) feature-selection, pruning, and weight-sharing. This can be viewed as an {\it a priori} argument in favor of those techniques.

Date: 1994-04
References: Add references at CitEc
Citations: View citations in EconPapers (1)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wop:safiwp:94-04-019

Access Statistics for this paper

More papers in Working Papers from Santa Fe Institute Contact information at EDIRC.
Bibliographic data for series maintained by Thomas Krichel ().