FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W69888316> ?p ?o ?g. }

• W69888316 abstract "The theory and practice of discriminant analysis have been mainly developed for two-class problems (computation of dichotomies). This phenomenon can easily be explained, since there is an obvious way to perform multi-category discrimination tasks using solely models computing dichotomies. It consists in dividing the problem at hand into several {it one-against-all} ones and applying a simple rule to construct the global discriminant function from the partial ones. Adopting a direct approach, however, should make it possible to improve the results, let them be theoretical (bounds on the expected risk) or practical (values of the empirical risk and the expected risk). Although multi-category extensions of the main models computing dichotomiesas in the case of multi-layer perceptrons, in other cases, this cannot be done readily but at the expense of the loss of part of the theoretical foundations. This is for instance the main shortcoming of the multi-category support vector machines developed so far. One of the major difficulties of multi-category discriminant analysis rests in the fact that it requires specific uniform convergence results. Indeed, the uniform strong laws of large numbers established for dichotomies do not extend nicely to multi-category problems. They become significantly looser. This is problematical indeed, since the question of the quality of bounds is of central importance if one wants to implement with confidence the structural risk minimization inductive principle, which is preciselyIn this paper, building upon the notions of margin used in the context of statistical learning theory and boosting theory, and the corresponding generalization error bounds, we derive sharper bounds on the expected risk (generalization error) of multi-class vector-valued discriminant models. The main result is an extension of a lemma by Bartlett. After a discussion about the notion of margin and its use for two-class discriminant analysis, we derive the main theorem and its corollaries. We then show how to bound the capacity measure for sets of functions of interest and study specifically the case of the multivariate linear regression model, which is of particular importance, since it is directly related to multi-category support vector machines. Finally, the bound is assessed on a real-worldThis work, which aims at establishing foundations for the statistical analysis of multi-class models, based on a new notion of margin, paves the way for the theoretical study of the existing multi-class support vector machines and the design of new ones. biocomputing problem. grounding the support vector method. can often be conceived simply," @default.
• W69888316 created "2016-06-24" @default.
• W69888316 creator A5044907764 @default.
• W69888316 creator A5048932953 @default.
• W69888316 creator A5084606226 @default.
• W69888316 date "2000-01-01" @default.
• W69888316 modified "2023-09-25" @default.
• W69888316 title "Margin Error and Generalization Capabilities of Multi-Class Discriminant Systems" @default.
• W69888316 hasPublicationYear "2000" @default.
• W69888316 type Work @default.
• W69888316 sameAs 69888316 @default.
• W69888316 citedByCount "5" @default.
• W69888316 crossrefType "journal-article" @default.
• W69888316 hasAuthorship W69888316A5044907764 @default.
• W69888316 hasAuthorship W69888316A5048932953 @default.
• W69888316 hasAuthorship W69888316A5084606226 @default.
• W69888316 hasConcept C105795698 @default.
• W69888316 hasConcept C119857082 @default.
• W69888316 hasConcept C12267149 @default.
• W69888316 hasConcept C134306372 @default.
• W69888316 hasConcept C151730666 @default.
• W69888316 hasConcept C154507838 @default.
• W69888316 hasConcept C154945302 @default.
• W69888316 hasConcept C177148314 @default.
• W69888316 hasConcept C199360897 @default.
• W69888316 hasConcept C2777212361 @default.
• W69888316 hasConcept C2779343474 @default.
• W69888316 hasConcept C2780801425 @default.
• W69888316 hasConcept C33923547 @default.
• W69888316 hasConcept C41008148 @default.
• W69888316 hasConcept C50644808 @default.
• W69888316 hasConcept C59462968 @default.
• W69888316 hasConcept C60908668 @default.
• W69888316 hasConcept C69738355 @default.
• W69888316 hasConcept C774472 @default.
• W69888316 hasConcept C78397625 @default.
• W69888316 hasConcept C86803240 @default.
• W69888316 hasConceptScore W69888316C105795698 @default.
• W69888316 hasConceptScore W69888316C119857082 @default.
• W69888316 hasConceptScore W69888316C12267149 @default.
• W69888316 hasConceptScore W69888316C134306372 @default.
• W69888316 hasConceptScore W69888316C151730666 @default.
• W69888316 hasConceptScore W69888316C154507838 @default.
• W69888316 hasConceptScore W69888316C154945302 @default.
• W69888316 hasConceptScore W69888316C177148314 @default.
• W69888316 hasConceptScore W69888316C199360897 @default.
• W69888316 hasConceptScore W69888316C2777212361 @default.
• W69888316 hasConceptScore W69888316C2779343474 @default.
• W69888316 hasConceptScore W69888316C2780801425 @default.
• W69888316 hasConceptScore W69888316C33923547 @default.
• W69888316 hasConceptScore W69888316C41008148 @default.
• W69888316 hasConceptScore W69888316C50644808 @default.
• W69888316 hasConceptScore W69888316C59462968 @default.
• W69888316 hasConceptScore W69888316C60908668 @default.
• W69888316 hasConceptScore W69888316C69738355 @default.
• W69888316 hasConceptScore W69888316C774472 @default.
• W69888316 hasConceptScore W69888316C78397625 @default.
• W69888316 hasConceptScore W69888316C86803240 @default.
• W69888316 hasLocation W698883161 @default.
• W69888316 hasOpenAccess W69888316 @default.
• W69888316 hasPrimaryLocation W698883161 @default.
• W69888316 hasRelatedWork W1529449589 @default.
• W69888316 hasRelatedWork W153437452 @default.
• W69888316 hasRelatedWork W1590024046 @default.
• W69888316 hasRelatedWork W1964119535 @default.
• W69888316 hasRelatedWork W1984519198 @default.
• W69888316 hasRelatedWork W2004597781 @default.
• W69888316 hasRelatedWork W2032633790 @default.
• W69888316 hasRelatedWork W2047737850 @default.
• W69888316 hasRelatedWork W2076896526 @default.
• W69888316 hasRelatedWork W2099579348 @default.
• W69888316 hasRelatedWork W2119596982 @default.
• W69888316 hasRelatedWork W2141981133 @default.
• W69888316 hasRelatedWork W2148603752 @default.
• W69888316 hasRelatedWork W2152226562 @default.
• W69888316 hasRelatedWork W2350751952 @default.
• W69888316 hasRelatedWork W2356922403 @default.
• W69888316 hasRelatedWork W2369271519 @default.
• W69888316 hasRelatedWork W2376687616 @default.
• W69888316 hasRelatedWork W2408521075 @default.
• W69888316 hasRelatedWork W2511535996 @default.
• W69888316 isParatext "false" @default.
• W69888316 isRetracted "false" @default.
• W69888316 magId "69888316" @default.
• W69888316 workType "article" @default.