Measuring the Hierarchy of Feedforward Networks

Details Measuring the Hierarchy of Feedforward Networks Measuring the Hierarchy of Feedforward Networks

2010-11-19

arxiv.org/abs/1011.4394v2

Physics

Data Analysis, Statistics and Probability

12 pages, 6 figures. Accepted for publication in Chaos Journal special issue "Mesoscales in Complex Networks". Previous incons

Scientific paper

10.1063/1.3562548

In this paper we explore the concept of hierarchy as a quantifiable descriptor of ordered structures, departing from the definition of three conditions to be satisfied for a hierarchical structure: {\em order}, {\em predictability} and {\em pyramidal structure}. According to these principles we define a hierarchical index taking concepts from graph and information theory. This estimator allows to quantify the hierarchical character of any system susceptible to be abstracted in a feedforward causal graph, i.e., a directed acyclic graph defined in a single connected structure. Our hierarchical index is a balance between this predictability and pyramidal condition by the definition of two entropies: one attending the onward flow and other for the backward reversion. We show how this index allows to identify hierarchical, anti-hierarchical and non hierarchical structures. Our formalism reveals that departing from the defined conditions for a hierarchical structure, feedforward trees and the inverted tree graphs emerge as the only causal structures of maximal hierarchical and anti-hierarchical systems, respectively. Conversely, null values of the hierarchical index are attributed to a number of different configuration networks; from linear chains, due to their lack of pyramid structure, to full-connected feedforward graphs where the diversity of onward pathways is canceled by the uncertainty (lack of predictability) when going backwards. Some illustrative examples are provided for the distinction among these three types of hierarchical causal graphs.

Affiliated with

Also associated with

No associations

Rating

Measuring the Hierarchy of Feedforward Networks does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Measuring the Hierarchy of Feedforward Networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Measuring the Hierarchy of Feedforward Networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-117114