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: |
2000-07
|
---|---|
Authors: | Shalizi, Cosma Rohilla ; Crutchfield, James P. |
Institutions: | Santa Fe Institute |
Saved in:
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)
-
Pattern Discovery and Computational Mechanics
Shalizi, Cosma Rohilla, (2000)
- More ...