Matches in SemOpenAlex for { <https://semopenalex.org/work/W144429020> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W144429020 endingPage "592" @default.
- W144429020 startingPage "582" @default.
- W144429020 abstract "This paper presents a neural network ensemble (NNE) construction method for classification problems. The proposed method automatically determines a minimal NNE architecture and thus called the Minimal Neural Network Ensemble Construction (MNNEC) method. To determine minimal architecture, it starts with a single neural network (NN) with a minimal number of hidden units. During training process, it adds additional NN(s) with cumulative number(s) of hidden units. In conventional methods, in contrast, the number of NNs for NNE and the number of hidden nodes for each NN should be predetermined. At the time of NN addition in MNNEC, the added NN specializes in the previously unsolved portion of the input space. Finally all the NNs are trained simultaneously to improve the generalization ability. Therefore, for easy problems when multiple NNs are not required and a single NN is sufficient, the MNNEC can generate a single NN with a minimal number of hidden units. The MNNEC has been tested extensively on several benchmark problems of machine learning and NNs. The results exhibit that the MNNEC is able to construct NNEs of much smaller size than conventional methods." @default.
- W144429020 created "2016-06-24" @default.
- W144429020 creator A5018767527 @default.
- W144429020 creator A5043721074 @default.
- W144429020 date "2007-07-20" @default.
- W144429020 modified "2023-09-23" @default.
- W144429020 title "A Minimal Neural Network Ensemble Construction Method: A Constructive Approach" @default.
- W144429020 cites W1967646346 @default.
- W144429020 cites W1992018127 @default.
- W144429020 cites W2044172252 @default.
- W144429020 cites W2058764642 @default.
- W144429020 cites W2061119986 @default.
- W144429020 cites W2100805904 @default.
- W144429020 cites W2117941247 @default.
- W144429020 cites W2134514463 @default.
- W144429020 cites W2142544077 @default.
- W144429020 cites W2151554678 @default.
- W144429020 cites W2167055186 @default.
- W144429020 cites W2168046285 @default.
- W144429020 cites W2171752105 @default.
- W144429020 cites W4212883601 @default.
- W144429020 doi "https://doi.org/10.20965/jaciii.2007.p0582" @default.
- W144429020 hasPublicationYear "2007" @default.
- W144429020 type Work @default.
- W144429020 sameAs 144429020 @default.
- W144429020 citedByCount "3" @default.
- W144429020 countsByYear W1444290202012 @default.
- W144429020 crossrefType "journal-article" @default.
- W144429020 hasAuthorship W144429020A5018767527 @default.
- W144429020 hasAuthorship W144429020A5043721074 @default.
- W144429020 hasBestOaLocation W1444290201 @default.
- W144429020 hasConcept C111919701 @default.
- W144429020 hasConcept C119857082 @default.
- W144429020 hasConcept C13280743 @default.
- W144429020 hasConcept C134306372 @default.
- W144429020 hasConcept C153180895 @default.
- W144429020 hasConcept C154945302 @default.
- W144429020 hasConcept C175202392 @default.
- W144429020 hasConcept C177148314 @default.
- W144429020 hasConcept C185798385 @default.
- W144429020 hasConcept C199360897 @default.
- W144429020 hasConcept C205649164 @default.
- W144429020 hasConcept C2778701210 @default.
- W144429020 hasConcept C2780801425 @default.
- W144429020 hasConcept C33923547 @default.
- W144429020 hasConcept C41008148 @default.
- W144429020 hasConcept C50644808 @default.
- W144429020 hasConcept C98045186 @default.
- W144429020 hasConceptScore W144429020C111919701 @default.
- W144429020 hasConceptScore W144429020C119857082 @default.
- W144429020 hasConceptScore W144429020C13280743 @default.
- W144429020 hasConceptScore W144429020C134306372 @default.
- W144429020 hasConceptScore W144429020C153180895 @default.
- W144429020 hasConceptScore W144429020C154945302 @default.
- W144429020 hasConceptScore W144429020C175202392 @default.
- W144429020 hasConceptScore W144429020C177148314 @default.
- W144429020 hasConceptScore W144429020C185798385 @default.
- W144429020 hasConceptScore W144429020C199360897 @default.
- W144429020 hasConceptScore W144429020C205649164 @default.
- W144429020 hasConceptScore W144429020C2778701210 @default.
- W144429020 hasConceptScore W144429020C2780801425 @default.
- W144429020 hasConceptScore W144429020C33923547 @default.
- W144429020 hasConceptScore W144429020C41008148 @default.
- W144429020 hasConceptScore W144429020C50644808 @default.
- W144429020 hasConceptScore W144429020C98045186 @default.
- W144429020 hasIssue "6" @default.
- W144429020 hasLocation W1444290201 @default.
- W144429020 hasOpenAccess W144429020 @default.
- W144429020 hasPrimaryLocation W1444290201 @default.
- W144429020 hasRelatedWork W1975025300 @default.
- W144429020 hasRelatedWork W2094559136 @default.
- W144429020 hasRelatedWork W2366803925 @default.
- W144429020 hasRelatedWork W2386387936 @default.
- W144429020 hasRelatedWork W3132254705 @default.
- W144429020 hasRelatedWork W4221150964 @default.
- W144429020 hasRelatedWork W4236038968 @default.
- W144429020 hasRelatedWork W4312365371 @default.
- W144429020 hasRelatedWork W4312903001 @default.
- W144429020 hasRelatedWork W1629725936 @default.
- W144429020 hasVolume "11" @default.
- W144429020 isParatext "false" @default.
- W144429020 isRetracted "false" @default.
- W144429020 magId "144429020" @default.
- W144429020 workType "article" @default.