Discovering Patterns by Searching for Simplicity

Alezander P. M. van den Bosch

I discuss the use of Kolmogorov complexity and Bayes’ theorem in Solomonoff’s inductive method to explicate a generM concept of simplicity. This makes it possible to understand how the search for simple, i.e., short, computational descriptions of (empirical) data yields to the discovery of patterns, and hence more probable predictions. I show how the simplicity bias of Langley’s BACON.2 and Thagard’s PI is subsumed by Rissanen’s Minimum Description Length principle, which is a computable approximation of Solomonoff’s uncomputable inductive method.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.