Nonlinear Memory Capacity of Parallel Time-Delay Reservoir Computers in the Processing of Multidimensional Signals

Grigoryeva, Lyudmila; Henriques, Julie; Larger, Laurent; Ortega, Juan-Pablo

Nonlinear Memory Capacity of Parallel Time-Delay Reservoir Computers in the Processing of Multidimensional Signals

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2016

Autor:innen

Grigoryeva, Lyudmila

Henriques, Julie

Larger, Laurent

Ortega, Juan-Pablo

DOI (zitierfähiger Link)

https://doi.org/10.1162/NECO_a_00845

Sammlungen

Mathematik und Statistik

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

Neural Computation. 2016, 28(7), pp. 1411-1451. ISSN 0899-7667. eISSN 1530-888X. Available under: doi: 10.1162/NECO_a_00845

Zusammenfassung

This letter addresses the reservoir design problem in the context of delay-based reservoir computers for multidimensional input signals, parallel architectures, and real-time multitasking. First, an approximating reservoir model is presented in those frameworks that provides an explicit functional link between the reservoir architecture and its performance in the execution of a specific task. Second, the inference properties of the ridge regression estimator in the multivariate context are used to assess the impact of finite sample training on the decrease of the reservoir capacity. Finally, an empirical study is conducted that shows the adequacy of the theoretical results with the empirical performances exhibited by various reservoir architectures in the execution of several nonlinear tasks with multidimensional inputs. Our results confirm the robustness properties of the parallel reservoir architecture with respect to task misspecification and parameter choice already documented in the literature.

Fachgebiet (DDC)

510 Mathematik

Zitieren

ISO 690

GRIGORYEVA, Lyudmila, Julie HENRIQUES, Laurent LARGER, Juan-Pablo ORTEGA, 2016. Nonlinear Memory Capacity of Parallel Time-Delay Reservoir Computers in the Processing of Multidimensional Signals. In: Neural Computation. 2016, 28(7), pp. 1411-1451. ISSN 0899-7667. eISSN 1530-888X. Available under: doi: 10.1162/NECO_a_00845

BibTex

@article{Grigoryeva2016-07Nonli-35211,
  year={2016},
  doi={10.1162/NECO_a_00845},
  title={Nonlinear Memory Capacity of Parallel Time-Delay Reservoir Computers in the Processing of Multidimensional Signals},
  number={7},
  volume={28},
  issn={0899-7667},
  journal={Neural Computation},
  pages={1411--1451},
  author={Grigoryeva, Lyudmila and Henriques, Julie and Larger, Laurent 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/123456789/35211">
    <dc:creator>Larger, Laurent</dc:creator>
    <dc:contributor>Larger, Laurent</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/39"/>
    <dc:contributor>Henriques, Julie</dc:contributor>
    <dcterms:abstract xml:lang="eng">This letter addresses the reservoir design problem in the context of delay-based reservoir computers for multidimensional input signals, parallel architectures, and real-time multitasking. First, an approximating reservoir model is presented in those frameworks that provides an explicit functional link between the reservoir architecture and its performance in the execution of a specific task. Second, the inference properties of the ridge regression estimator in the multivariate context are used to assess the impact of finite sample training on the decrease of the reservoir capacity. Finally, an empirical study is conducted that shows the adequacy of the theoretical results with the empirical performances exhibited by various reservoir architectures in the execution of several nonlinear tasks with multidimensional inputs. Our results confirm the robustness properties of the parallel reservoir architecture with respect to task misspecification and parameter choice already documented in the literature.</dcterms:abstract>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2016-09-12T09:48:12Z</dcterms:available>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/39"/>
    <dc:contributor>Ortega, Juan-Pablo</dc:contributor>
    <dc:contributor>Grigoryeva, Lyudmila</dc:contributor>
    <dcterms:issued>2016-07</dcterms:issued>
    <dc:creator>Ortega, Juan-Pablo</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2016-09-12T09:48:12Z</dc:date>
    <dcterms:title>Nonlinear Memory Capacity of Parallel Time-Delay Reservoir Computers in the Processing of Multidimensional Signals</dcterms:title>
    <dc:creator>Grigoryeva, Lyudmila</dc:creator>
    <dc:creator>Henriques, Julie</dc:creator>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/35211"/>
    <dc:language>eng</dc:language>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja