University of Surrey

Test tubes in the lab Research in the ATI Dance Research

A measure of statistical complexity based on predictive information

Abdallah, SA and Plumbley, MD (2010) A measure of statistical complexity based on predictive information [Report]

Full text not available from this repository.

Abstract

We introduce an information theoretic measure of statistical structure, called 'binding information', for sets of random variables, and compare it with several previously proposed measures including excess entropy, Bialek et al.'s predictive information, and the multi-information. We derive some of the properties of the binding information, particularly in relation to the multi-information, and show that, for finite sets of binary random variables, the processes which maximises binding information are the 'parity' processes. Finally we discuss some of the implications this has for the use of the binding information as a measure of complexity.

Item Type: Report
Authors :
NameEmailORCID
Abdallah, SAUNSPECIFIEDUNSPECIFIED
Plumbley, MDm.plumbley@surrey.ac.ukUNSPECIFIED
Date : 8 December 2010
Uncontrolled Keywords : math.ST, math.ST, cs.IT, math.IT, physics.data-an, stat.TH
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 13:19
Last Modified : 17 May 2017 15:10
URI: http://epubs.surrey.ac.uk/id/eprint/838763

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800