Reexamination of an information geometric construction of entropic indicators of complexity

被引：16
|
作者：
Cafaro, C. [1 ]
Giffin, A. [2 ]
Ali, S. A. [3 ]
Kim, D. -H. [4 ]
机构：
[1] Univ Camerino, Dipartimento Fis, I-62032 Camerino, Italy
[2] Princeton Univ, Princeton Inst Sci & Technol Mat, Princeton, NJ 08540 USA
[3] SUNY Albany, Dept Phys, Albany, NY 12222 USA
[4] Sogang Univ, Ctr Quantum Spacetime, Seoul 121742, South Korea
来源：
APPLIED MATHEMATICS AND COMPUTATION | 2010年 / 217卷 / 07期
关键词：
Probability theory; Riemannian geometry; Chaos; Complexity; Entropy; STATISTICAL MANIFOLDS; CHAOS; INFERENCE; PREDICTABILITY;
D O I：
10.1016/j.amc.2010.08.028
中图分类号：
O29 [应用数学];
学科分类号：
070104 ;
摘要：
Information geometry and inductive inference methods can be used to model dynamical systems in terms of their probabilistic description on curved statistical manifolds. In this article, we present a formal conceptual reexamination of the information geometric construction of entropic indicators of complexity for statistical models. Specifically, we present conceptual advances in the interpretation of the information geometric entropy (IGE), a statistical indicator of temporal complexity (chaoticity) defined on curved statistical manifolds underlying the probabilistic dynamics of physical systems. (C) 2010 Elsevier Inc. All rights reserved.
引用
收藏
页码：2944 / 2951
页数：8
相关论文
共 50 条
12345