Matches in SemOpenAlex for { <https://semopenalex.org/work/W2547910352> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2547910352 endingPage "1392" @default.
- W2547910352 startingPage "1385" @default.
- W2547910352 abstract "Metric learning has been shown to significantly improve the accuracy of k-nearest neighbor (kNN) classification. In problems involving thousands of features, distance learning algorithms cannot be used due to overfitting and high computational complexity. In such cases, previous work has relied on a two-step solution: first apply dimensionality reduction methods to the data, and then learn a metric in the resulting low-dimensional subspace. In this paper we show that better classification performance can be achieved by unifying the objectives of dimensionality reduction and metric learning. We propose a method that solves for the low-dimensional projection of the inputs, which minimizes a metric objective aimed at separating points in different classes by a large margin. This projection is defined by a significantly smaller number of parameters than metrics learned in input space, and thus our optimization reduces the risks of overfitting. Theory and results are presented for both a linear as well as a kernelized version of the algorithm. Overall, we achieve classification rates similar, and in several cases superior, to those of support vector machines." @default.
- W2547910352 created "2016-11-11" @default.
- W2547910352 creator A5044005697 @default.
- W2547910352 creator A5045413165 @default.
- W2547910352 creator A5073032636 @default.
- W2547910352 date "2007-01-01" @default.
- W2547910352 modified "2023-09-27" @default.
- W2547910352 title "Large Margin Component Analysis" @default.
- W2547910352 hasPublicationYear "2007" @default.
- W2547910352 type Work @default.
- W2547910352 sameAs 2547910352 @default.
- W2547910352 citedByCount "0" @default.
- W2547910352 crossrefType "journal-article" @default.
- W2547910352 hasAuthorship W2547910352A5044005697 @default.
- W2547910352 hasAuthorship W2547910352A5045413165 @default.
- W2547910352 hasAuthorship W2547910352A5073032636 @default.
- W2547910352 hasConcept C111030470 @default.
- W2547910352 hasConcept C113238511 @default.
- W2547910352 hasConcept C11413529 @default.
- W2547910352 hasConcept C119857082 @default.
- W2547910352 hasConcept C12267149 @default.
- W2547910352 hasConcept C153180895 @default.
- W2547910352 hasConcept C154945302 @default.
- W2547910352 hasConcept C162324750 @default.
- W2547910352 hasConcept C176217482 @default.
- W2547910352 hasConcept C21547014 @default.
- W2547910352 hasConcept C22019652 @default.
- W2547910352 hasConcept C32834561 @default.
- W2547910352 hasConcept C33923547 @default.
- W2547910352 hasConcept C41008148 @default.
- W2547910352 hasConcept C50644808 @default.
- W2547910352 hasConcept C57493831 @default.
- W2547910352 hasConcept C70518039 @default.
- W2547910352 hasConcept C774472 @default.
- W2547910352 hasConcept C94475309 @default.
- W2547910352 hasConceptScore W2547910352C111030470 @default.
- W2547910352 hasConceptScore W2547910352C113238511 @default.
- W2547910352 hasConceptScore W2547910352C11413529 @default.
- W2547910352 hasConceptScore W2547910352C119857082 @default.
- W2547910352 hasConceptScore W2547910352C12267149 @default.
- W2547910352 hasConceptScore W2547910352C153180895 @default.
- W2547910352 hasConceptScore W2547910352C154945302 @default.
- W2547910352 hasConceptScore W2547910352C162324750 @default.
- W2547910352 hasConceptScore W2547910352C176217482 @default.
- W2547910352 hasConceptScore W2547910352C21547014 @default.
- W2547910352 hasConceptScore W2547910352C22019652 @default.
- W2547910352 hasConceptScore W2547910352C32834561 @default.
- W2547910352 hasConceptScore W2547910352C33923547 @default.
- W2547910352 hasConceptScore W2547910352C41008148 @default.
- W2547910352 hasConceptScore W2547910352C50644808 @default.
- W2547910352 hasConceptScore W2547910352C57493831 @default.
- W2547910352 hasConceptScore W2547910352C70518039 @default.
- W2547910352 hasConceptScore W2547910352C774472 @default.
- W2547910352 hasConceptScore W2547910352C94475309 @default.
- W2547910352 hasLocation W25479103521 @default.
- W2547910352 hasOpenAccess W2547910352 @default.
- W2547910352 hasPrimaryLocation W25479103521 @default.
- W2547910352 hasRelatedWork W1485810016 @default.
- W2547910352 hasRelatedWork W1529507376 @default.
- W2547910352 hasRelatedWork W1537346900 @default.
- W2547910352 hasRelatedWork W1543818407 @default.
- W2547910352 hasRelatedWork W2016729848 @default.
- W2547910352 hasRelatedWork W2048812019 @default.
- W2547910352 hasRelatedWork W2123068691 @default.
- W2547910352 hasRelatedWork W2136261952 @default.
- W2547910352 hasRelatedWork W2259994334 @default.
- W2547910352 hasRelatedWork W2287707734 @default.
- W2547910352 hasRelatedWork W2592215762 @default.
- W2547910352 hasRelatedWork W2801977764 @default.
- W2547910352 hasRelatedWork W2809077420 @default.
- W2547910352 hasRelatedWork W2884224972 @default.
- W2547910352 hasRelatedWork W2906559318 @default.
- W2547910352 hasRelatedWork W2906580195 @default.
- W2547910352 hasRelatedWork W2949001095 @default.
- W2547910352 hasRelatedWork W2951058014 @default.
- W2547910352 hasRelatedWork W2989766428 @default.
- W2547910352 hasRelatedWork W3106820385 @default.
- W2547910352 isParatext "false" @default.
- W2547910352 isRetracted "false" @default.
- W2547910352 magId "2547910352" @default.
- W2547910352 workType "article" @default.