Reservoir Computing : Information Processing of Stationary Signals

Zitieren

Dateien zu dieser Ressource

Dateien Größe Format Anzeige

Zu diesem Dokument gibt es keine Dateien.

GRIGORYEVA, Lyudmila, Julie HENRIQUES, Juan-Pablo ORTEGA, 2016. Reservoir Computing : Information Processing of Stationary Signals. IEEE International Conference on Computational Science and Engineering (CSE 2016). Paris, France, 24. Aug 2016 - 26. Aug 2016. In: Proceedings : 19th IEEE International Conference on Computational Science and Engineering, 14th IEEE International Conference on Embedded and Ubiquitous Computing, 15th International Symposium on Distributed Computing and Applications to Business, Engineering and Science ; CSE-EUC-DCABES 2016. Piscataway, NJ:IEEE, pp. 496-503. ISBN 978-1-5090-3593-9. Available under: doi: 10.1109/CSE-EUC-DCABES.2016.231

@inproceedings{Grigoryeva2016-08Reser-40644, title={Reservoir Computing : Information Processing of Stationary Signals}, year={2016}, doi={10.1109/CSE-EUC-DCABES.2016.231}, isbn={978-1-5090-3593-9}, address={Piscataway, NJ}, publisher={IEEE}, booktitle={Proceedings : 19th IEEE International Conference on Computational Science and Engineering, 14th IEEE International Conference on Embedded and Ubiquitous Computing, 15th International Symposium on Distributed Computing and Applications to Business, Engineering and Science ; CSE-EUC-DCABES 2016}, pages={496--503}, author={Grigoryeva, Lyudmila and Henriques, Julie and Ortega, Juan-Pablo} }

<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/rdf/resource/123456789/40644"> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/39"/> <dcterms:issued>2016-08</dcterms:issued> <dcterms:abstract xml:lang="eng">This paper extends the notion of information processing capacity for non-independent input signals in the context of reservoir computing (RC). The presence of input autocorrelation makes worthwhile the treatment of forecasting and filtering problems for which we explicitly compute this generalized capacity as a function of the reservoir parameter values using a streamlined model. The reservoir model leading to these developments is used to show that, whenever that approximation is valid, this computational paradigm satisfies the so called separation and fading memory properties that are usually associated with good information processing performances. We show that several standard memory, forecasting, and filtering problems that appear in the parametric stochastic time series context can be readily formulated and tackled via RC which, as we show, significantly outperforms standard techniques in some instances.</dcterms:abstract> <dcterms:title>Reservoir Computing : Information Processing of Stationary Signals</dcterms:title> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-11-16T13:25:28Z</dc:date> <dc:contributor>Henriques, Julie</dc:contributor> <dc:creator>Henriques, Julie</dc:creator> <dc:creator>Ortega, Juan-Pablo</dc:creator> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/39"/> <dc:contributor>Ortega, Juan-Pablo</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-11-16T13:25:28Z</dcterms:available> <dc:language>eng</dc:language> <dc:contributor>Grigoryeva, Lyudmila</dc:contributor> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/40644"/> <dc:creator>Grigoryeva, Lyudmila</dc:creator> </rdf:Description> </rdf:RDF>

Das Dokument erscheint in:

KOPS Suche


Stöbern

Mein Benutzerkonto