Matches in SemOpenAlex for { <https://semopenalex.org/work/W1985367615> ?p ?o ?g. }
- W1985367615 endingPage "1458" @default.
- W1985367615 startingPage "1443" @default.
- W1985367615 abstract "We describe approaches for positive data modeling and classification using both finite inverted Dirichlet mixture models and support vector machines (SVMs). Inverted Dirichlet mixture models are used to tackle an outstanding challenge in SVMs namely the generation of accurate kernels. The kernels generation approaches, grounded on ideas from information theory that we consider, allow the incorporation of data structure and its structural constraints. Inverted Dirichlet mixture models are learned within a principled Bayesian framework using both Gibbs sampler and Metropolis-Hastings for parameter estimation and Bayes factor for model selection (i.e., determining the number of mixture’s components). Our Bayesian learning approach uses priors, which we derive by showing that the inverted Dirichlet distribution belongs to the family of exponential distributions, over the model parameters, and then combines these priors with information from the data to build posterior distributions. We illustrate the merits and the effectiveness of the proposed method with two real-world challenging applications namely object detection and visual scenes analysis and classification." @default.
- W1985367615 created "2016-06-24" @default.
- W1985367615 creator A5001475115 @default.
- W1985367615 creator A5090600716 @default.
- W1985367615 date "2012-08-10" @default.
- W1985367615 modified "2023-10-17" @default.
- W1985367615 title "Bayesian learning of inverted Dirichlet mixtures for SVM kernels generation" @default.
- W1985367615 cites W1508404128 @default.
- W1985367615 cites W1512606473 @default.
- W1985367615 cites W1536156198 @default.
- W1985367615 cites W1547388036 @default.
- W1985367615 cites W1567323455 @default.
- W1985367615 cites W1584333058 @default.
- W1985367615 cites W1596052433 @default.
- W1985367615 cites W1882901045 @default.
- W1985367615 cites W1886306325 @default.
- W1985367615 cites W1963566461 @default.
- W1985367615 cites W1975968782 @default.
- W1985367615 cites W1980801609 @default.
- W1985367615 cites W1983655951 @default.
- W1985367615 cites W2000911694 @default.
- W1985367615 cites W2001983900 @default.
- W1985367615 cites W2004326702 @default.
- W1985367615 cites W2012672587 @default.
- W1985367615 cites W2016728733 @default.
- W1985367615 cites W2029164135 @default.
- W1985367615 cites W2035893370 @default.
- W1985367615 cites W2041323157 @default.
- W1985367615 cites W2043432627 @default.
- W1985367615 cites W2054658115 @default.
- W1985367615 cites W2058732827 @default.
- W1985367615 cites W2060161465 @default.
- W1985367615 cites W2060556149 @default.
- W1985367615 cites W2067389767 @default.
- W1985367615 cites W2070612147 @default.
- W1985367615 cites W2074282020 @default.
- W1985367615 cites W207560109 @default.
- W1985367615 cites W2078963943 @default.
- W1985367615 cites W2086125239 @default.
- W1985367615 cites W2096295934 @default.
- W1985367615 cites W2105488551 @default.
- W1985367615 cites W2107034620 @default.
- W1985367615 cites W2112074816 @default.
- W1985367615 cites W2113132439 @default.
- W1985367615 cites W2128272608 @default.
- W1985367615 cites W2131842293 @default.
- W1985367615 cites W2136097953 @default.
- W1985367615 cites W2138753389 @default.
- W1985367615 cites W2146950091 @default.
- W1985367615 cites W2147238549 @default.
- W1985367615 cites W2147993235 @default.
- W1985367615 cites W2148227735 @default.
- W1985367615 cites W2151103935 @default.
- W1985367615 cites W2151768982 @default.
- W1985367615 cites W2152594362 @default.
- W1985367615 cites W2154683974 @default.
- W1985367615 cites W2157686535 @default.
- W1985367615 cites W2159379488 @default.
- W1985367615 cites W2162915993 @default.
- W1985367615 cites W2166761907 @default.
- W1985367615 cites W2169135276 @default.
- W1985367615 cites W2169714360 @default.
- W1985367615 cites W2171343216 @default.
- W1985367615 cites W2488678869 @default.
- W1985367615 cites W2493170222 @default.
- W1985367615 cites W4211177544 @default.
- W1985367615 cites W4233518571 @default.
- W1985367615 cites W78553138 @default.
- W1985367615 doi "https://doi.org/10.1007/s00521-012-1094-z" @default.
- W1985367615 hasPublicationYear "2012" @default.
- W1985367615 type Work @default.
- W1985367615 sameAs 1985367615 @default.
- W1985367615 citedByCount "53" @default.
- W1985367615 countsByYear W19853676152012 @default.
- W1985367615 countsByYear W19853676152014 @default.
- W1985367615 countsByYear W19853676152015 @default.
- W1985367615 countsByYear W19853676152016 @default.
- W1985367615 countsByYear W19853676152017 @default.
- W1985367615 countsByYear W19853676152018 @default.
- W1985367615 countsByYear W19853676152019 @default.
- W1985367615 countsByYear W19853676152020 @default.
- W1985367615 countsByYear W19853676152021 @default.
- W1985367615 countsByYear W19853676152022 @default.
- W1985367615 crossrefType "journal-article" @default.
- W1985367615 hasAuthorship W1985367615A5001475115 @default.
- W1985367615 hasAuthorship W1985367615A5090600716 @default.
- W1985367615 hasBestOaLocation W19853676152 @default.
- W1985367615 hasConcept C107673813 @default.
- W1985367615 hasConcept C119857082 @default.
- W1985367615 hasConcept C12267149 @default.
- W1985367615 hasConcept C134306372 @default.
- W1985367615 hasConcept C141318989 @default.
- W1985367615 hasConcept C153180895 @default.
- W1985367615 hasConcept C154945302 @default.
- W1985367615 hasConcept C158424031 @default.
- W1985367615 hasConcept C169214877 @default.
- W1985367615 hasConcept C171686336 @default.
- W1985367615 hasConcept C177769412 @default.