Measuring the hierarchy of feedforward networks

DOI10.1063/1.3562548zbMATH Open1345.93003arXiv1011.4394OpenAlexW3104771188WikidataQ83763752 ScholiaQ83763752MaRDI QIDQ2821522FDOQ2821522

Authors: Bernat Corominas-Murtra, Carlos Rodríguez-Caso, Joaquín Goñi, Ricard Solé 

Publication date: 21 September 2016

Published in: Chaos (Search for Journal in Brave)

Abstract: 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.

Full work available at URL: https://arxiv.org/abs/1011.4394

Recommendations

• The capacity of feedforward neural networks
• scientific article; zbMATH DE number 2018620
• Feedforward neural structures in binary hypothesis testing
• Establishing impacts of the inputs in a feedforward neural network
• Enumeration of connected feedforward networks
• The hidden layer size in feed-forward neural networks: A statistical point of view
• Dynamics of a neural network with hierarchically stored patterns

Mathematics Subject Classification ID

Directed graphs (digraphs), tournaments (05C20) Measures of information, entropy (94A17) Hierarchical systems (93A13)

Cites Work

• A Mathematical Theory of Communication
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (1)

• On the origins of hierarchy in complex networks

This page was built for publication: Measuring the hierarchy of feedforward networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2821522)