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.

MoreLess

Year of publication:	2000-07
Authors:	Shalizi, Cosma Rohilla ; Crutchfield, James P.
Institutions:	Santa Fe Institute

More details

Series:	Working Papers.
Type of publication:	Book / Working Paper
Source:	RePEc - Research Papers in Economics

Persistent link: https://ebvufind01.dmz1.zbw.eu/10005790865