INFORMATION BOTTLENECKS, CAUSAL STATES, AND STATISTICAL RELEVANCE BASES: HOW TO REPRESENT RELEVANT INFORMATION IN MEMORYLESS TRANSDUCTION
Discovering relevant, but possibly hidden, variables is a key step in constructing useful and predictive theories about the natural world. This brief note explains the connections between three approaches to this problem: the recently introduced information-bottleneck method, the computational mechanics approach to inferring optimal models, and Salmon's statistical relevance basis.
Year of publication: |
2002
|
---|---|
Authors: | SHALIZI, COSMA ROHILLA ; CRUTCHFIELD, JAMES P. |
Published in: |
Advances in Complex Systems (ACS). - World Scientific Publishing Co. Pte. Ltd., ISSN 1793-6802. - Vol. 05.2002, 01, p. 91-95
|
Publisher: |
World Scientific Publishing Co. Pte. Ltd. |
Subject: | Information bottleneck | causal state | statistical relevance | memoryless transduction |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Computational Mechanics: Pattern and Prediction, Structure and Simplicity
Shalizi, Cosma Rohilla, (1999)
-
Comments on ``Simple Measure for Complexity''
Crutchfield, James P., (1999)
-
Thermodynamic Depth of Causal States: When Paddling Around in Occam's Pool Shallowness Is a Virtue
Crutchfield, James P., (1998)
- More ...