Publikation: Impact of neuron models and network structure on evolving modular robot neural network controllers
Lade...
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2012
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
SOULE, Terence, ed. and others. GECCO '12 : Proceedings of the 14th annual conference on Genetic and evolutionary computation. New York, NY: ACM, 2012, pp. 89-96. ISBN 978-1-4503-1177-9. Available under: doi: 10.1145/2330163.2330177
Zusammenfassung
This paper investigates the properties required to evolve Artificial Neural Networks for distributed control in modular robotics, which typically involves non-linear dynamics and complex interactions in the sensori-motor space. We investigate the relation between macro-scale properties (such as modularity and regularity) and micro-scale properties in Neural Network controllers. We show how neurons capable of multiplicative-like arithmetic operations may increase the performance of controllers in several ways whenever challenging control problems with non-linear dynamics are involved. This paper provides evidence that performance and robustness of evolved controllers can be improved by a combination of carefully chosen micro- and macro-scale neural network properties.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
GECCO '12 : 14th annual conference on Genetic and evolutionary computation, 7. Juli 2012 - 11. Juli 2012, Philadelphia, Pennsylvania
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690
CAZENILLE, Leo, Nicolas BREDECHE, Heiko HAMANN, Jürgen STRADNER, 2012. Impact of neuron models and network structure on evolving modular robot neural network controllers. GECCO '12 : 14th annual conference on Genetic and evolutionary computation. Philadelphia, Pennsylvania, 7. Juli 2012 - 11. Juli 2012. In: SOULE, Terence, ed. and others. GECCO '12 : Proceedings of the 14th annual conference on Genetic and evolutionary computation. New York, NY: ACM, 2012, pp. 89-96. ISBN 978-1-4503-1177-9. Available under: doi: 10.1145/2330163.2330177BibTex
@inproceedings{Cazenille2012Impac-59916,
year={2012},
doi={10.1145/2330163.2330177},
title={Impact of neuron models and network structure on evolving modular robot neural network controllers},
isbn={978-1-4503-1177-9},
publisher={ACM},
address={New York, NY},
booktitle={GECCO '12 : Proceedings of the 14th annual conference on Genetic and evolutionary computation},
pages={89--96},
editor={Soule, Terence},
author={Cazenille, Leo and Bredeche, Nicolas and Hamann, Heiko and Stradner, Jürgen}
}RDF
<rdf:RDF
xmlns:dcterms="http://purl.org/dc/terms/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:bibo="http://purl.org/ontology/bibo/"
xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
xmlns:foaf="http://xmlns.com/foaf/0.1/"
xmlns:void="http://rdfs.org/ns/void#"
xmlns:xsd="http://www.w3.org/2001/XMLSchema#" >
<rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/59916">
<dc:rights>terms-of-use</dc:rights>
<dc:contributor>Bredeche, Nicolas</dc:contributor>
<dcterms:abstract xml:lang="eng">This paper investigates the properties required to evolve Artificial Neural Networks for distributed control in modular robotics, which typically involves non-linear dynamics and complex interactions in the sensori-motor space. We investigate the relation between macro-scale properties (such as modularity and regularity) and micro-scale properties in Neural Network controllers. We show how neurons capable of multiplicative-like arithmetic operations may increase the performance of controllers in several ways whenever challenging control problems with non-linear dynamics are involved. This paper provides evidence that performance and robustness of evolved controllers can be improved by a combination of carefully chosen micro- and macro-scale neural network properties.</dcterms:abstract>
<dcterms:issued>2012</dcterms:issued>
<dc:creator>Hamann, Heiko</dc:creator>
<dc:contributor>Hamann, Heiko</dc:contributor>
<dc:creator>Cazenille, Leo</dc:creator>
<bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/59916"/>
<dc:creator>Bredeche, Nicolas</dc:creator>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dcterms:title>Impact of neuron models and network structure on evolving modular robot neural network controllers</dcterms:title>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-24T13:27:17Z</dc:date>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-24T13:27:17Z</dcterms:available>
<dc:language>eng</dc:language>
<dc:contributor>Stradner, Jürgen</dc:contributor>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:creator>Stradner, Jürgen</dc:creator>
<dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dc:contributor>Cazenille, Leo</dc:contributor>
</rdf:Description>
</rdf:RDF>Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Nein
