Work

Information Bottlenecks, Causal States, and Statistical Relevance Bases: How to Represent Relevant Information in Memoryless Transduction

Year: 2002

Type: article

Abstract: 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.

Source: Advances in Complex Systems

DOI: 10.1142/s0219525902000481

Authors: COSMA ROHILLA SHALIZI, JAMES P. CRUTCHFIELD

Institution: Santa Fe Institute

Language: English

Topic: Philosophy and History of Science

Subfield: History and Philosophy of Science

Field: Arts and Humanities

Domain: Social Sciences

Open Access status: green

OpenAlex ID: W1530254650

FWCI: 8.874

Cites: 19

Cited by: 33

Related to: 10