Matches in SemOpenAlex for { <https://semopenalex.org/work/W2059680488> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2059680488 abstract "Structural Support Vector Machines (SSVMs) have become a popular tool in machine learning for predicting structured objects like parse trees, Part-of-Speech (POS) label sequences and image segments. Various efficient algorithmic techniques have been proposed for training SSVMs for large datasets. The typical SSVM formulation contains a regularizer term and a composite loss term. The loss term is usually composed of the Linear Maximum Error (LME) associated with the training examples. Other alternatives for the loss term are yet to be explored for SSVMs. We formulate a new SSVM with Linear Summed Error (LSE) loss term and propose efficient algorithms to train the new SSVM formulation using primal cutting-plane method and sequential dual coordinate descent method. Numerical experiments on benchmark datasets demonstrate that the sequential dual coordinate descent method is faster than the cutting-plane method and reaches the steady-state generalization performance faster. It is thus a useful alternative for training SSVMs when linear summed error is used." @default.
- W2059680488 created "2016-06-24" @default.
- W2059680488 creator A5004972422 @default.
- W2059680488 creator A5026126465 @default.
- W2059680488 creator A5052364789 @default.
- W2059680488 date "2012-06-01" @default.
- W2059680488 modified "2023-09-26" @default.
- W2059680488 title "Efficient algorithms for linear summed error structural SVMs" @default.
- W2059680488 cites W1518470882 @default.
- W2059680488 cites W1934019294 @default.
- W2059680488 cites W2027552332 @default.
- W2059680488 cites W2031248101 @default.
- W2059680488 cites W2035720976 @default.
- W2059680488 cites W2044502056 @default.
- W2059680488 cites W2115364117 @default.
- W2059680488 cites W2123729042 @default.
- W2059680488 cites W2127091553 @default.
- W2059680488 cites W2142557384 @default.
- W2059680488 cites W2146851241 @default.
- W2059680488 cites W2147880316 @default.
- W2059680488 cites W2152540201 @default.
- W2059680488 cites W2165966284 @default.
- W2059680488 cites W2282078507 @default.
- W2059680488 cites W2343954916 @default.
- W2059680488 doi "https://doi.org/10.1109/ijcnn.2012.6252830" @default.
- W2059680488 hasPublicationYear "2012" @default.
- W2059680488 type Work @default.
- W2059680488 sameAs 2059680488 @default.
- W2059680488 citedByCount "0" @default.
- W2059680488 crossrefType "proceedings-article" @default.
- W2059680488 hasAuthorship W2059680488A5004972422 @default.
- W2059680488 hasAuthorship W2059680488A5026126465 @default.
- W2059680488 hasAuthorship W2059680488A5052364789 @default.
- W2059680488 hasConcept C11413529 @default.
- W2059680488 hasConcept C121332964 @default.
- W2059680488 hasConcept C12267149 @default.
- W2059680488 hasConcept C124952713 @default.
- W2059680488 hasConcept C13280743 @default.
- W2059680488 hasConcept C134306372 @default.
- W2059680488 hasConcept C142362112 @default.
- W2059680488 hasConcept C153180895 @default.
- W2059680488 hasConcept C153258448 @default.
- W2059680488 hasConcept C154945302 @default.
- W2059680488 hasConcept C157553263 @default.
- W2059680488 hasConcept C177148314 @default.
- W2059680488 hasConcept C185798385 @default.
- W2059680488 hasConcept C205649164 @default.
- W2059680488 hasConcept C2780980858 @default.
- W2059680488 hasConcept C33923547 @default.
- W2059680488 hasConcept C41008148 @default.
- W2059680488 hasConcept C50644808 @default.
- W2059680488 hasConcept C61797465 @default.
- W2059680488 hasConcept C62520636 @default.
- W2059680488 hasConceptScore W2059680488C11413529 @default.
- W2059680488 hasConceptScore W2059680488C121332964 @default.
- W2059680488 hasConceptScore W2059680488C12267149 @default.
- W2059680488 hasConceptScore W2059680488C124952713 @default.
- W2059680488 hasConceptScore W2059680488C13280743 @default.
- W2059680488 hasConceptScore W2059680488C134306372 @default.
- W2059680488 hasConceptScore W2059680488C142362112 @default.
- W2059680488 hasConceptScore W2059680488C153180895 @default.
- W2059680488 hasConceptScore W2059680488C153258448 @default.
- W2059680488 hasConceptScore W2059680488C154945302 @default.
- W2059680488 hasConceptScore W2059680488C157553263 @default.
- W2059680488 hasConceptScore W2059680488C177148314 @default.
- W2059680488 hasConceptScore W2059680488C185798385 @default.
- W2059680488 hasConceptScore W2059680488C205649164 @default.
- W2059680488 hasConceptScore W2059680488C2780980858 @default.
- W2059680488 hasConceptScore W2059680488C33923547 @default.
- W2059680488 hasConceptScore W2059680488C41008148 @default.
- W2059680488 hasConceptScore W2059680488C50644808 @default.
- W2059680488 hasConceptScore W2059680488C61797465 @default.
- W2059680488 hasConceptScore W2059680488C62520636 @default.
- W2059680488 hasLocation W20596804881 @default.
- W2059680488 hasOpenAccess W2059680488 @default.
- W2059680488 hasPrimaryLocation W20596804881 @default.
- W2059680488 hasRelatedWork W1556122387 @default.
- W2059680488 hasRelatedWork W1724210103 @default.
- W2059680488 hasRelatedWork W1965981978 @default.
- W2059680488 hasRelatedWork W1972581644 @default.
- W2059680488 hasRelatedWork W2014395529 @default.
- W2059680488 hasRelatedWork W2022268906 @default.
- W2059680488 hasRelatedWork W2024161402 @default.
- W2059680488 hasRelatedWork W2040838894 @default.
- W2059680488 hasRelatedWork W2041417488 @default.
- W2059680488 hasRelatedWork W2089747945 @default.
- W2059680488 hasRelatedWork W2108844857 @default.
- W2059680488 hasRelatedWork W2119748693 @default.
- W2059680488 hasRelatedWork W2122024048 @default.
- W2059680488 hasRelatedWork W2134767360 @default.
- W2059680488 hasRelatedWork W2426910956 @default.
- W2059680488 hasRelatedWork W2505554796 @default.
- W2059680488 hasRelatedWork W2511615393 @default.
- W2059680488 hasRelatedWork W2537717744 @default.
- W2059680488 hasRelatedWork W2624853940 @default.
- W2059680488 hasRelatedWork W3147134082 @default.
- W2059680488 isParatext "false" @default.
- W2059680488 isRetracted "false" @default.
- W2059680488 magId "2059680488" @default.
- W2059680488 workType "article" @default.