Information flows in causal networks

被引：164

作者：

Ay, Nihat ^{[1
,2
]}

Polani, Daniel ^{[3
]}

机构：

[1] Max Planck Inst Math Sci, D-04103 Leipzig, Germany

[2] Santa Fe Inst, Santa Fe, NM 87501 USA

[3] Univ Hertfordshire, Sch Comp Sci, Algorithms & Adapt Syst Res Grp, Hatfield AL10 9AB, Herts, England

来源：

ADVANCES IN COMPLEX SYSTEMS | 2008年 / 11卷 / 01期

关键词：

causality; information theory; information flow; Bayesian networks;

D O I：

10.1142/S0219525908001465

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

We use a notion of causal independence based on intervention, which is a fundamental concept of the theory of causal networks, to define a measure for the strength of a causal effect. We call this measure "information flow" and compare it with known information flow measures such as transfer entropy.

引用

页码：17 / 41

页数：25

共 29 条

[1] [Anonymous], COMPLEXITY ENTROPY P
[2] ASHYBY WR, 1952, DESIGN BRAIN
[3] Could information theory provide an ecological theory of sensory processing?
Aticky, Joseph J.
[J]. NETWORK-COMPUTATION IN NEURAL SYSTEMS, 2011, 22 (1-4) : 4 - 44
[4] Dynamical properties of strongly interacting Markov chains
Ay, N
Wennekers, T
[J]. NEURAL NETWORKS, 2003, 16 (10) : 1483 - 1497
[5] Geometric robustness theory and biological networks
Ay, Nihat
Krakauer, David C.
[J]. THEORY IN BIOSCIENCES, 2007, 125 (02) : 93 - 121
[6] Baddeley R., 2000, Information theory and the brain
[7] Barlow H., 1959, SENS COMMUN, P217
[8] Der R, 1999, CONCUR SYST ENGN SER, V55, P43
[9] Axioms of causal relevance
Galles, D
Pearl, J
[J]. ARTIFICIAL INTELLIGENCE, 1997, 97 (1-2) : 9 - 43
[10] Representations of space and time in the maximization of information flow in the perception-action loop
Klyubin, Alexander S.
Polani, Daniel
Nehaniv, Chrystopher L.
[J]. NEURAL COMPUTATION, 2007, 19 (09) : 2387 - 2432

← 1 2 3 →