Matches in SemOpenAlex for { <https://semopenalex.org/work/W2026854879> ?p ?o ?g. }
- W2026854879 endingPage "9" @default.
- W2026854879 startingPage "3" @default.
- W2026854879 abstract "The initial localized generalization error model (LGEM) aims to find an upper bound of error between a target function and a radial basis function neural network (RBFNN) within a neighborhood of the training samples. The contribution of LGEM can be briefly described as that the generalization error is less than or equal to the summation of three terms: training error, stochastic sensitivity measure (SSM), and a constant. This paper extends the initial LGEM to a new LGEM model for single-hidden layer feed-forward neural networks (SLFNs) trained with extreme learning machine (ELM) which is a type of new training algorithms without iterations. The development of this extended LGEM can provide some useful guidelines for improving the generalization ability of SLFNs trained with ELM. An algorithm for architecture selection of the SLFNs is also proposed based on the extended LGEM. Experimental results on a number of benchmark data sets show that an approximately optimal architecture in terms of number of neurons of a SLFN can be found using our method. Furthermore, the experimental results on eleven UCI data sets show that the proposed method is effective and efficient." @default.
- W2026854879 created "2016-06-24" @default.
- W2026854879 creator A5017499347 @default.
- W2026854879 creator A5032693528 @default.
- W2026854879 creator A5073006299 @default.
- W2026854879 creator A5086792725 @default.
- W2026854879 date "2013-02-01" @default.
- W2026854879 modified "2023-10-05" @default.
- W2026854879 title "Architecture selection for networks trained with extreme learning machine using localized generalization error model" @default.
- W2026854879 cites W1971476226 @default.
- W2026854879 cites W1986733754 @default.
- W2026854879 cites W1990938413 @default.
- W2026854879 cites W1993717606 @default.
- W2026854879 cites W2002728347 @default.
- W2026854879 cites W2035026907 @default.
- W2026854879 cites W2039590377 @default.
- W2026854879 cites W2046699673 @default.
- W2026854879 cites W2046904226 @default.
- W2026854879 cites W2059800482 @default.
- W2026854879 cites W2064644935 @default.
- W2026854879 cites W2065292742 @default.
- W2026854879 cites W2076118331 @default.
- W2026854879 cites W2077812306 @default.
- W2026854879 cites W2093578608 @default.
- W2026854879 cites W2096987757 @default.
- W2026854879 cites W2111072639 @default.
- W2026854879 cites W2122040390 @default.
- W2026854879 cites W2130378394 @default.
- W2026854879 cites W2135017202 @default.
- W2026854879 cites W2141695047 @default.
- W2026854879 cites W2169976759 @default.
- W2026854879 cites W2171604354 @default.
- W2026854879 cites W4233413206 @default.
- W2026854879 doi "https://doi.org/10.1016/j.neucom.2011.12.053" @default.
- W2026854879 hasPublicationYear "2013" @default.
- W2026854879 type Work @default.
- W2026854879 sameAs 2026854879 @default.
- W2026854879 citedByCount "69" @default.
- W2026854879 countsByYear W20268548792012 @default.
- W2026854879 countsByYear W20268548792014 @default.
- W2026854879 countsByYear W20268548792015 @default.
- W2026854879 countsByYear W20268548792016 @default.
- W2026854879 countsByYear W20268548792017 @default.
- W2026854879 countsByYear W20268548792018 @default.
- W2026854879 countsByYear W20268548792019 @default.
- W2026854879 countsByYear W20268548792020 @default.
- W2026854879 countsByYear W20268548792021 @default.
- W2026854879 countsByYear W20268548792022 @default.
- W2026854879 countsByYear W20268548792023 @default.
- W2026854879 crossrefType "journal-article" @default.
- W2026854879 hasAuthorship W2026854879A5017499347 @default.
- W2026854879 hasAuthorship W2026854879A5032693528 @default.
- W2026854879 hasAuthorship W2026854879A5073006299 @default.
- W2026854879 hasAuthorship W2026854879A5086792725 @default.
- W2026854879 hasConcept C117765406 @default.
- W2026854879 hasConcept C119857082 @default.
- W2026854879 hasConcept C13280743 @default.
- W2026854879 hasConcept C134306372 @default.
- W2026854879 hasConcept C14036430 @default.
- W2026854879 hasConcept C153180895 @default.
- W2026854879 hasConcept C154945302 @default.
- W2026854879 hasConcept C177148314 @default.
- W2026854879 hasConcept C185798385 @default.
- W2026854879 hasConcept C205649164 @default.
- W2026854879 hasConcept C2780150128 @default.
- W2026854879 hasConcept C33923547 @default.
- W2026854879 hasConcept C41008148 @default.
- W2026854879 hasConcept C50644808 @default.
- W2026854879 hasConcept C5465570 @default.
- W2026854879 hasConcept C78458016 @default.
- W2026854879 hasConcept C81917197 @default.
- W2026854879 hasConcept C86803240 @default.
- W2026854879 hasConcept C98856871 @default.
- W2026854879 hasConceptScore W2026854879C117765406 @default.
- W2026854879 hasConceptScore W2026854879C119857082 @default.
- W2026854879 hasConceptScore W2026854879C13280743 @default.
- W2026854879 hasConceptScore W2026854879C134306372 @default.
- W2026854879 hasConceptScore W2026854879C14036430 @default.
- W2026854879 hasConceptScore W2026854879C153180895 @default.
- W2026854879 hasConceptScore W2026854879C154945302 @default.
- W2026854879 hasConceptScore W2026854879C177148314 @default.
- W2026854879 hasConceptScore W2026854879C185798385 @default.
- W2026854879 hasConceptScore W2026854879C205649164 @default.
- W2026854879 hasConceptScore W2026854879C2780150128 @default.
- W2026854879 hasConceptScore W2026854879C33923547 @default.
- W2026854879 hasConceptScore W2026854879C41008148 @default.
- W2026854879 hasConceptScore W2026854879C50644808 @default.
- W2026854879 hasConceptScore W2026854879C5465570 @default.
- W2026854879 hasConceptScore W2026854879C78458016 @default.
- W2026854879 hasConceptScore W2026854879C81917197 @default.
- W2026854879 hasConceptScore W2026854879C86803240 @default.
- W2026854879 hasConceptScore W2026854879C98856871 @default.
- W2026854879 hasLocation W20268548791 @default.
- W2026854879 hasOpenAccess W2026854879 @default.
- W2026854879 hasPrimaryLocation W20268548791 @default.
- W2026854879 hasRelatedWork W1525510058 @default.
- W2026854879 hasRelatedWork W1591671037 @default.
- W2026854879 hasRelatedWork W2026854879 @default.