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

[11] Klyubin AS, 2004, 2004 NASA/DOD CONFERENCE ON EVOLVABLE HARDWARE, PROCEEDINGS, P177
[12] Klyubin AS, 2005, IEEE C EVOL COMPUTAT, P128
[13] Bayesian integration in sensorimotor learning
Körding, KP
Wolpert, DM
[J]. NATURE, 2004, 427 (6971) : 244 - 247
[14] Information transfer between dynamical system components
Liang, XS
Kleeman, R
[J]. PHYSICAL REVIEW LETTERS, 2005, 95 (24)
[15] SELF-ORGANIZATION IN A PERCEPTUAL NETWORK
LINSKER, R
[J]. COMPUTER, 1988, 21 (03) : 105 - 117
[16] LLOYD S, 1991, NATO ADV SCI I B-PHY, V256, P131
[17] CALCULATION OF INFORMATION-FLOW RATE FROM MUTUAL INFORMATION
MATSUMOTO, K
TSUDA, I
[J]. JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1988, 21 (06): : 1405 - 1414
[18] MCGILL WJ, 1954, IEEE T INFORM THEORY, V4, P93
[19] Olsson L, 2004, 2004 NASA/DOD CONFERENCE ON EVOLVABLE HARDWARE, PROCEEDINGS, P153
[20] Pearl J., 2000, Models, reasoning and inference

← 1 2 3 →