Matches in SemOpenAlex for { <https://semopenalex.org/work/W2066162502> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2066162502 abstract "A batch training algorithm for feed-forward networks is proposed which uses Newton's method to estimate a vector of optimal learning factors, one for each hidden unit. Backpropagation, using this learning factor vector, is used to modify the hidden unit's input weights. Linear equations are then solved for the network's output weights. Elements of the new method's Gauss-Newton Hessian matrix are shown to be weighted sums of elements from the total network's Hessian. In several examples, the new method performs better than backpropagation and conjugate gradient, with similar numbers of required multiplies. The method performs as well as or better than Levenberg-Marquardt, with several orders of magnitude fewer multiplies due to the small size of its Hessian." @default.
- W2066162502 created "2016-06-24" @default.
- W2066162502 creator A5036559796 @default.
- W2066162502 creator A5042213267 @default.
- W2066162502 date "2010-04-05" @default.
- W2066162502 modified "2023-09-23" @default.
- W2066162502 title "Multiple optimal learning factors for feed-forward networks" @default.
- W2066162502 cites W122552260 @default.
- W2066162502 cites W1500731913 @default.
- W2066162502 cites W1515851936 @default.
- W2066162502 cites W1567333323 @default.
- W2066162502 cites W1985030154 @default.
- W2066162502 cites W1988268958 @default.
- W2066162502 cites W2006544565 @default.
- W2066162502 cites W2077658674 @default.
- W2066162502 cites W2087070363 @default.
- W2066162502 cites W2103496339 @default.
- W2066162502 cites W2125392132 @default.
- W2066162502 cites W2141278204 @default.
- W2066162502 cites W2153904408 @default.
- W2066162502 cites W2163113711 @default.
- W2066162502 cites W2256578114 @default.
- W2066162502 cites W2316564661 @default.
- W2066162502 cites W2484226612 @default.
- W2066162502 cites W2766736793 @default.
- W2066162502 cites W3012317737 @default.
- W2066162502 doi "https://doi.org/10.1117/12.850873" @default.
- W2066162502 hasPublicationYear "2010" @default.
- W2066162502 type Work @default.
- W2066162502 sameAs 2066162502 @default.
- W2066162502 citedByCount "19" @default.
- W2066162502 countsByYear W20661625022013 @default.
- W2066162502 countsByYear W20661625022014 @default.
- W2066162502 countsByYear W20661625022015 @default.
- W2066162502 countsByYear W20661625022016 @default.
- W2066162502 countsByYear W20661625022017 @default.
- W2066162502 countsByYear W20661625022019 @default.
- W2066162502 countsByYear W20661625022021 @default.
- W2066162502 countsByYear W20661625022022 @default.
- W2066162502 crossrefType "proceedings-article" @default.
- W2066162502 hasAuthorship W2066162502A5036559796 @default.
- W2066162502 hasAuthorship W2066162502A5042213267 @default.
- W2066162502 hasConcept C106487976 @default.
- W2066162502 hasConcept C11413529 @default.
- W2066162502 hasConcept C126255220 @default.
- W2066162502 hasConcept C153258448 @default.
- W2066162502 hasConcept C154945302 @default.
- W2066162502 hasConcept C155032097 @default.
- W2066162502 hasConcept C159985019 @default.
- W2066162502 hasConcept C192562407 @default.
- W2066162502 hasConcept C203616005 @default.
- W2066162502 hasConcept C28826006 @default.
- W2066162502 hasConcept C33923547 @default.
- W2066162502 hasConcept C41008148 @default.
- W2066162502 hasConcept C50644808 @default.
- W2066162502 hasConcept C81184566 @default.
- W2066162502 hasConceptScore W2066162502C106487976 @default.
- W2066162502 hasConceptScore W2066162502C11413529 @default.
- W2066162502 hasConceptScore W2066162502C126255220 @default.
- W2066162502 hasConceptScore W2066162502C153258448 @default.
- W2066162502 hasConceptScore W2066162502C154945302 @default.
- W2066162502 hasConceptScore W2066162502C155032097 @default.
- W2066162502 hasConceptScore W2066162502C159985019 @default.
- W2066162502 hasConceptScore W2066162502C192562407 @default.
- W2066162502 hasConceptScore W2066162502C203616005 @default.
- W2066162502 hasConceptScore W2066162502C28826006 @default.
- W2066162502 hasConceptScore W2066162502C33923547 @default.
- W2066162502 hasConceptScore W2066162502C41008148 @default.
- W2066162502 hasConceptScore W2066162502C50644808 @default.
- W2066162502 hasConceptScore W2066162502C81184566 @default.
- W2066162502 hasLocation W20661625021 @default.
- W2066162502 hasOpenAccess W2066162502 @default.
- W2066162502 hasPrimaryLocation W20661625021 @default.
- W2066162502 hasRelatedWork W2018863220 @default.
- W2066162502 hasRelatedWork W2099604242 @default.
- W2066162502 hasRelatedWork W2126070502 @default.
- W2066162502 hasRelatedWork W2133761359 @default.
- W2066162502 hasRelatedWork W2184451860 @default.
- W2066162502 hasRelatedWork W2554138451 @default.
- W2066162502 hasRelatedWork W2782273464 @default.
- W2066162502 hasRelatedWork W324943035 @default.
- W2066162502 hasRelatedWork W2185955524 @default.
- W2066162502 hasRelatedWork W2890893481 @default.
- W2066162502 isParatext "false" @default.
- W2066162502 isRetracted "false" @default.
- W2066162502 magId "2066162502" @default.
- W2066162502 workType "article" @default.