INFORMATION BOTTLENECKS, CAUSAL STATES, AND STATISTICAL RELEVANCE BASES: HOW TO REPRESENT RELEVANT INFORMATION IN MEMORYLESS TRANSDUCTION
2002 ◽
Vol 05
(01)
◽
pp. 91-95
◽
Keyword(s):
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.
Keyword(s):
2010 ◽
Vol 22
(8)
◽
pp. 1961-1992
◽
Keyword(s):
Keyword(s):
1994 ◽
Vol 52
◽
pp. 900-901
2016 ◽
Vol 30
(4)
◽
pp. 141-154
◽
Keyword(s):
2010 ◽
Vol 24
(3)
◽
pp. 161-172
◽
2020 ◽
Vol 228
(1)
◽
pp. 43-49
◽
Keyword(s):