Combining Discriminant Models with New Multi-Class SVMs
Identifieur interne : 002F10 ( Istex/Curation ); précédent : 002F09; suivant : 002F11Combining Discriminant Models with New Multi-Class SVMs
Auteurs : Yann GuermeurSource :
- Pattern Analysis & Applications [ 1433-7541 ] ; 2002-06-01.
English descriptors
Abstract
Abstract:: The idea of performing model combination, instead of model selection, has a long theoretical background in statistics. However, making use of theoretical results is ordinarily subject to the satisfaction of strong hypotheses (weak error correlation, availability of large training sets, possibility to rerun the training procedure an arbitrary number of times, etc.). In contrast, the practitioner is frequently faced with the problem of combining a given set of pre-trained classifiers, with highly correlated errors, using only a small training sample. Overfitting is then the main risk, which cannot be overcome but with a strict complexity control of the combiner selected. This suggests that SVMs should be well suited for these difficult situations. Investigating this idea, we introduce a family of multi-class SVMs and assess them as ensemble methods on a real-world problem. This task, protein secondary structure prediction, is an open problem in biocomputing for which model combination appears to be an issue of central importance. Experimental evidence highlights the gain in quality resulting from combining some of the most widely used prediction methods with our SVMs rather than with the ensemble methods traditionally used in the field. The gain increases when the outputs of the combiners are post-processed with a DP algorithm.
Url:
DOI: 10.1007/s100440200015
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: Pour aller vers cette notice dans l'étape Curation :002F48
Links to Exploration step
ISTEX:C7D3AF7CF44572C374B709E44525FB21342D8189Curation
No country items
Yann Guermeur<affiliation><mods:affiliation>LORIA, Campus Scientifique, Vandœvre-lès-Nancy, France, FR</mods:affiliation>
<wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Combining Discriminant Models with New Multi-Class SVMs</title>
<author><name sortKey="Guermeur, Yann" sort="Guermeur, Yann" uniqKey="Guermeur Y" first="Yann" last="Guermeur">Yann Guermeur</name>
<affiliation><mods:affiliation>LORIA, Campus Scientifique, Vandœvre-lès-Nancy, France, FR</mods:affiliation>
<wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:C7D3AF7CF44572C374B709E44525FB21342D8189</idno>
<date when="2002" year="2002">2002</date>
<idno type="doi">10.1007/s100440200015</idno>
<idno type="url">https://api.istex.fr/ark:/67375/VQC-D2M77J1N-P/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002F48</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">002F48</idno>
<idno type="wicri:Area/Istex/Curation">002F10</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Combining Discriminant Models with New Multi-Class SVMs</title>
<author><name sortKey="Guermeur, Yann" sort="Guermeur, Yann" uniqKey="Guermeur Y" first="Yann" last="Guermeur">Yann Guermeur</name>
<affiliation><mods:affiliation>LORIA, Campus Scientifique, Vandœvre-lès-Nancy, France, FR</mods:affiliation>
<wicri:noCountry code="subField">FR</wicri:noCountry>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j">Pattern Analysis & Applications</title>
<title level="j" type="abbrev">Pattern Anal Appl</title>
<idno type="ISSN">1433-7541</idno>
<imprint><publisher>Springer-Verlag London Limited</publisher>
<pubPlace>London</pubPlace>
<date type="published" when="2002-06-01">2002-06-01</date>
<biblScope unit="volume">5</biblScope>
<biblScope unit="issue">2</biblScope>
<biblScope unit="page" from="168">168</biblScope>
<biblScope unit="page" to="179">179</biblScope>
</imprint>
<idno type="ISSN">1433-7541</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">1433-7541</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Key words: Classifier fusion; Generalisation performance; Hierarchical sequence processing systems; Protein secondary structure prediction; Statistical learning theory; Support Vector Machines</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract:: The idea of performing model combination, instead of model selection, has a long theoretical background in statistics. However, making use of theoretical results is ordinarily subject to the satisfaction of strong hypotheses (weak error correlation, availability of large training sets, possibility to rerun the training procedure an arbitrary number of times, etc.). In contrast, the practitioner is frequently faced with the problem of combining a given set of pre-trained classifiers, with highly correlated errors, using only a small training sample. Overfitting is then the main risk, which cannot be overcome but with a strict complexity control of the combiner selected. This suggests that SVMs should be well suited for these difficult situations. Investigating this idea, we introduce a family of multi-class SVMs and assess them as ensemble methods on a real-world problem. This task, protein secondary structure prediction, is an open problem in biocomputing for which model combination appears to be an issue of central importance. Experimental evidence highlights the gain in quality resulting from combining some of the most widely used prediction methods with our SVMs rather than with the ensemble methods traditionally used in the field. The gain increases when the outputs of the combiners are post-processed with a DP algorithm.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Istex/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002F10 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Curation/biblio.hfd -nk 002F10 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Istex |étape= Curation |type= RBID |clé= ISTEX:C7D3AF7CF44572C374B709E44525FB21342D8189 |texte= Combining Discriminant Models with New Multi-Class SVMs }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |