Merging Echo State and Feedforward Neural Networks for Time Series Forecasting
Identifieur interne : 002033 ( Main/Exploration ); précédent : 002032; suivant : 002034Merging Echo State and Feedforward Neural Networks for Time Series Forecasting
Auteurs : Štefan Babinec [Slovaquie] ; Ji Pospíchal [Slovaquie]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2006.
Abstract
Abstract: Echo state neural networks, which are a special case of recurrent neural networks, are studied from the viewpoint of their learning ability, with a goal to achieve their greater prediction ability. A standard training of these neural networks uses pseudoinverse matrix for one-step learning of weights from hidden to output neurons. Such learning was substituted by backpropagation of error learning algorithm and output neurons were replaced by feedforward neural network. This approach was tested in temperature forecasting, and the prediction error was substantially smaller in comparison with the prediction error achieved either by a standard echo state neural network, or by a standard multi-layered perceptron with backpropagation.
Url:
DOI: 10.1007/11840817_39
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002178
- to stream Istex, to step Curation: 002178
- to stream Istex, to step Checkpoint: 001598
- to stream Main, to step Merge: 002039
- to stream Main, to step Curation: 002033
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Merging Echo State and Feedforward Neural Networks for Time Series Forecasting</title><author><name sortKey="Babinec, Stefan" sort="Babinec, Stefan" uniqKey="Babinec S" first="Štefan" last="Babinec">Štefan Babinec</name></author><author><name sortKey="Pospichal, Ji" sort="Pospichal, Ji" uniqKey="Pospichal J" first="Ji" last="Pospíchal">Ji Pospíchal</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:CEC20AC8CF70F54C5BBA8F4CAAEB79EE18914C90</idno><date when="2006" year="2006">2006</date><idno type="doi">10.1007/11840817_39</idno><idno type="url">https://api.istex.fr/document/CEC20AC8CF70F54C5BBA8F4CAAEB79EE18914C90/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">002178</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">002178</idno><idno type="wicri:Area/Istex/Curation">002178</idno><idno type="wicri:Area/Istex/Checkpoint">001598</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">001598</idno><idno type="wicri:doubleKey">0302-9743:2006:Babinec S:merging:echo:state</idno><idno type="wicri:Area/Main/Merge">002039</idno><idno type="wicri:Area/Main/Curation">002033</idno><idno type="wicri:Area/Main/Exploration">002033</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Merging Echo State and Feedforward Neural Networks for Time Series Forecasting</title><author><name sortKey="Babinec, Stefan" sort="Babinec, Stefan" uniqKey="Babinec S" first="Štefan" last="Babinec">Štefan Babinec</name><affiliation wicri:level="1"><country xml:lang="fr">Slovaquie</country><wicri:regionArea>Department of Mathematics, Fac. of Chemical and Food Technologies, Slovak University of Technology, 812 37, Bratislava</wicri:regionArea><wicri:noRegion>Bratislava</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Slovaquie</country></affiliation></author><author><name sortKey="Pospichal, Ji" sort="Pospichal, Ji" uniqKey="Pospichal J" first="Ji" last="Pospíchal">Ji Pospíchal</name><affiliation wicri:level="1"><country xml:lang="fr">Slovaquie</country><wicri:regionArea>Institute of Applied Informatics, Fac. of Informatics and Information Technologies, Slovak University of Technology, 842 16, Bratislava</wicri:regionArea><wicri:noRegion>Bratislava</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Slovaquie</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2006</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">CEC20AC8CF70F54C5BBA8F4CAAEB79EE18914C90</idno><idno type="DOI">10.1007/11840817_39</idno><idno type="ChapterID">39</idno><idno type="ChapterID">Chap39</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Echo state neural networks, which are a special case of recurrent neural networks, are studied from the viewpoint of their learning ability, with a goal to achieve their greater prediction ability. A standard training of these neural networks uses pseudoinverse matrix for one-step learning of weights from hidden to output neurons. Such learning was substituted by backpropagation of error learning algorithm and output neurons were replaced by feedforward neural network. This approach was tested in temperature forecasting, and the prediction error was substantially smaller in comparison with the prediction error achieved either by a standard echo state neural network, or by a standard multi-layered perceptron with backpropagation.</div></front></TEI><affiliations><list><country><li>Slovaquie</li></country></list><tree><country name="Slovaquie"><noRegion><name sortKey="Babinec, Stefan" sort="Babinec, Stefan" uniqKey="Babinec S" first="Štefan" last="Babinec">Štefan Babinec</name></noRegion><name sortKey="Babinec, Stefan" sort="Babinec, Stefan" uniqKey="Babinec S" first="Štefan" last="Babinec">Štefan Babinec</name><name sortKey="Pospichal, Ji" sort="Pospichal, Ji" uniqKey="Pospichal J" first="Ji" last="Pospíchal">Ji Pospíchal</name><name sortKey="Pospichal, Ji" sort="Pospichal, Ji" uniqKey="Pospichal J" first="Ji" last="Pospíchal">Ji Pospíchal</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/TelematiV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002033 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002033 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= TelematiV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:CEC20AC8CF70F54C5BBA8F4CAAEB79EE18914C90
|texte= Merging Echo State and Feedforward Neural Networks for Time Series Forecasting
}}
| This area was generated with Dilib version V0.6.31. |  |