Pattern Discovery and Computational Mechanics
Abstract
Computational mechanics is a method for discovering, describing and quantifying patterns, using tools from statistical physics. It constructs optimal, minimal models of stochastic processes and their underlying causal structures. These models tell us about the intrinsic computation embedded within a process---how it stores and transforms information. Here we summarize the mathematics of computational mechanics, especially recent optimality and uniqueness results. We also expound the principles and motivations underlying computational mechanics, emphasizing its connections to the minimum description length principle, PAC theory, and other aspects of machine learning.
Cite
@article{arxiv.cs/0001027,
title = {Pattern Discovery and Computational Mechanics},
author = {Cosma Rohilla Shalizi and James P. Crutchfield},
journal= {arXiv preprint arXiv:cs/0001027},
year = {2007}
}
Comments
12 pages, 3 figures; submitted to the Proceedings of the 17th International Conference on Machine Learning (differs slightly in pagination and citation format from that version)