Echo state networks are universal

Grigoryeva, Lyudmila; Ortega, Juan-Pablo

Echo state networks are universal

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2018

Autor:innen

Grigoryeva, Lyudmila

Ortega, Juan-Pablo

DOI (zitierfähiger Link)

10.1016/j.neunet.2018.08.025

Sammlungen

Mathematik und Statistik

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

Neural Networks ; 108 (2018). - S. 495-508. - ISSN 0893-6080. - eISSN 1879-2782

Zusammenfassung

This paper shows that echo state networks are universal uniform approximants in the context of discrete-time fading memory filters with uniformly bounded inputs defined on negative infinite times. This result guarantees that any fading memory input/output system in discrete time can be realized as a simple finite-dimensional neural network-type state-space model with a static linear readout map. This approximation is valid for infinite time intervals. The proof of this statement is based on fundamental results, also presented in this work, about the topological nature of the fading memory property and about reservoir computing systems generated by continuous reservoir maps.

Fachgebiet (DDC)

510 Mathematik

Schlagwörter

Reservoir computing (RC), Universality, Echo state networks (ESN), Machine learning, Fading memory filters, Uniform system approximation

Zitieren

ISO 690

GRIGORYEVA, Lyudmila, Juan-Pablo ORTEGA, 2018. Echo state networks are universal. In: Neural Networks. 108, pp. 495-508. ISSN 0893-6080. eISSN 1879-2782. Available under: doi: 10.1016/j.neunet.2018.08.025

BibTex

@article{Grigoryeva2018-12state-44156,
  year={2018},
  doi={10.1016/j.neunet.2018.08.025},
  title={Echo state networks are universal},
  volume={108},
  issn={0893-6080},
  journal={Neural Networks},
  pages={495--508},
  author={Grigoryeva, Lyudmila and Ortega, Juan-Pablo}
}

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/123456789/44156">
    <dcterms:abstract xml:lang="eng">This paper shows that echo state networks are universal uniform approximants in the context of discrete-time fading memory filters with uniformly bounded inputs defined on negative infinite times. This result guarantees that any fading memory input/output system in discrete time can be realized as a simple finite-dimensional neural network-type state-space model with a static linear readout map. This approximation is valid for infinite time intervals. The proof of this statement is based on fundamental results, also presented in this work, about the topological nature of the fading memory property and about reservoir computing systems generated by continuous reservoir maps.</dcterms:abstract>
    <dc:creator>Ortega, Juan-Pablo</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:language>eng</dc:language>
    <dcterms:issued>2018-12</dcterms:issued>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-12-05T14:08:21Z</dcterms:available>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/39"/>
    <dc:creator>Grigoryeva, Lyudmila</dc:creator>
    <dc:contributor>Grigoryeva, Lyudmila</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-12-05T14:08:21Z</dc:date>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/44156"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/39"/>
    <dcterms:title>Echo state networks are universal</dcterms:title>
    <dc:contributor>Ortega, Juan-Pablo</dc:contributor>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja

Begutachtet

Ja