Dimension Reduction for Regression with Bottleneck Neural Networks
Identifieur interne : 000748 ( Main/Exploration ); précédent : 000747; suivant : 000749Dimension Reduction for Regression with Bottleneck Neural Networks
Auteurs : Elina Parviainen [Finlande]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2010.
Abstract
Abstract: Dimension reduction for regression (DRR) deals with the problem of finding for high-dimensional data such low-dimensional representations, which preserve the ability to predict a target variable. We propose doing DRR using a neural network with a low-dimensional “bottleneck” layer. While the network is trained for regression, the bottleneck learns a low-dimensional representation for the data. We compare our method to Covariance Operator Inverse Regression (COIR), which has been reported to perform well compared to many other DRR methods. The bottleneck network compares favorably with COIR: it is applicable to larger data sets, it is less sensitive to tuning parameters and it gives better results on several real data sets.
Url:
DOI: 10.1007/978-3-642-15381-5_5
Affiliations:
Links toward previous steps (curation, corpus...)
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Dimension Reduction for Regression with Bottleneck Neural Networks</title><author><name sortKey="Parviainen, Elina" sort="Parviainen, Elina" uniqKey="Parviainen E" first="Elina" last="Parviainen">Elina Parviainen</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:14A0F5285908E0D9275C01A4109950E90D585A16</idno><date when="2010" year="2010">2010</date><idno type="doi">10.1007/978-3-642-15381-5_5</idno><idno type="url">https://api.istex.fr/document/14A0F5285908E0D9275C01A4109950E90D585A16/fulltext/pdf</idno><idno type="wicri:Area/Main/Corpus">002F69</idno><idno type="wicri:Area/Main/Curation">002B79</idno><idno type="wicri:Area/Main/Exploration">000748</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Dimension Reduction for Regression with Bottleneck Neural Networks</title><author><name sortKey="Parviainen, Elina" sort="Parviainen, Elina" uniqKey="Parviainen E" first="Elina" last="Parviainen">Elina Parviainen</name><affiliation wicri:level="1"><country xml:lang="fr">Finlande</country><wicri:regionArea>BECS, Aalto University School of Science and Technology</wicri:regionArea><wicri:noRegion>Aalto University School of Science and Technology</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2010</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">14A0F5285908E0D9275C01A4109950E90D585A16</idno><idno type="DOI">10.1007/978-3-642-15381-5_5</idno><idno type="ChapterID">Chap5</idno><idno type="ChapterID">5</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: Dimension reduction for regression (DRR) deals with the problem of finding for high-dimensional data such low-dimensional representations, which preserve the ability to predict a target variable. We propose doing DRR using a neural network with a low-dimensional “bottleneck” layer. While the network is trained for regression, the bottleneck learns a low-dimensional representation for the data. We compare our method to Covariance Operator Inverse Regression (COIR), which has been reported to perform well compared to many other DRR methods. The bottleneck network compares favorably with COIR: it is applicable to larger data sets, it is less sensitive to tuning parameters and it gives better results on several real data sets.</div></front></TEI><affiliations><list><country><li>Finlande</li></country></list><tree><country name="Finlande"><noRegion><name sortKey="Parviainen, Elina" sort="Parviainen, Elina" uniqKey="Parviainen E" first="Elina" last="Parviainen">Elina Parviainen</name></noRegion></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sante/explor/ParkinsonV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000748 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000748 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Sante
|area= ParkinsonV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:14A0F5285908E0D9275C01A4109950E90D585A16
|texte= Dimension Reduction for Regression with Bottleneck Neural Networks
}}
| This area was generated with Dilib version V0.6.23. |  |