Measuring representation

Lars Marstaller, Arend Hintze, Christoph Adami

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

1 Downloads (Pure)

Abstract

We present a measure of representation in neural networks that we call ‘R’, which is based on information theory. We show how R relates to an analysis of distributed representation, viz. a principal components analysis of activation space. Finally, we argue that R is well suited to measure representation in neural networks.
Original languageEnglish
Title of host publicationASCS09
Subtitle of host publicationproceedings of the 9th Conference of the Australasian Society for Cognitive Science
EditorsWayne Christensen, Elizabeth Schier, John Sutton
Place of PublicationNorth Ryde, NSW
PublisherMacquarie Centre for Cognitive Science
Pages232-237
Number of pages6
ISBN (Print)9780646529189
DOIs
Publication statusPublished - 2010
Externally publishedYes
EventConference of the Australasian Society for Cognitive Science (9th : 2009) - Sydney
Duration: 30 Sep 20092 Oct 2009

Conference

ConferenceConference of the Australasian Society for Cognitive Science (9th : 2009)
CitySydney
Period30/09/092/10/09

Bibliographical note

Copyright 2009 by the Australasian Society for Cognitive Science. Publisher version archived with the permission of the Editor, ASCS09 : Proceedings of the 9th Conference of the Australasian Society for Cognitive Science. This copy is available for individual, non-commercial use. Permission to reprint/republish this version for other uses must be obtained from the publisher.

Keywords

  • artificial neural networks
  • (distributed) representation
  • information theory
  • principal components analysis
  • measure

Fingerprint Dive into the research topics of 'Measuring representation'. Together they form a unique fingerprint.

Cite this