BibTeX
@MISC{Peduault_inferringprobabilistic,
author = {Edwin P. D. Peduault},
title = {Inferring Probabilistic Theories from},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
When formulating a theory based on observations influenced by noise or other sources of uncertainty, it becomes necessary to decide whether the pro-posed theory agrees with the data “well enough.” This paper presents a criterion for making this judgement. The criterion is based on a gambling scenario involving an infinite sequence of observa-tions. In addition, a rule derived from the idea of minimal-length representations is presented for se-lecting an appropriate theory based on a finite set of observations. A proof is briefly outlined demon-strating that the theories selected by the rule obey the success criterion given a sufficient number of observations. 1.
