Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036590103> ?p ?o ?g. }
- W3036590103 endingPage "386" @default.
- W3036590103 startingPage "361" @default.
- W3036590103 abstract "In this paper, we propose a new multilevel Levenberg–Marquardt optimizer for the training of artificial neural networks with quadratic loss function. This setting allows us to get further insight into the potential of multilevel optimization methods. Indeed, when the least squares problem arises from the training of artificial neural networks, the variables subject to optimization are not related by any geometrical constraints and the standard interpolation and restriction operators cannot be employed any longer. A heuristic, inspired by algebraic multigrid methods, is then proposed to construct the multilevel transfer operators. We test the new optimizer on an important application: the approximate solution of partial differential equations by means of artificial neural networks. The learning problem is formulated as a least squares problem, choosing the nonlinear residual of the equation as a loss function, whereas the multilevel method is employed as a training method. Numerical experiments show encouraging results related to the efficiency of the new multilevel optimization method compared to the corresponding one-level procedure in this context." @default.
- W3036590103 created "2020-06-25" @default.
- W3036590103 creator A5005918238 @default.
- W3036590103 creator A5024258728 @default.
- W3036590103 creator A5036298459 @default.
- W3036590103 creator A5090885683 @default.
- W3036590103 date "2020-06-22" @default.
- W3036590103 modified "2023-10-18" @default.
- W3036590103 title "On a multilevel Levenberg–Marquardt method for the training of artificial neural networks and its application to the solution of partial differential equations" @default.
- W3036590103 cites W1970454553 @default.
- W3036590103 cites W1976792725 @default.
- W3036590103 cites W1978075626 @default.
- W3036590103 cites W1980427518 @default.
- W3036590103 cites W1997542937 @default.
- W3036590103 cites W1998720717 @default.
- W3036590103 cites W2003106321 @default.
- W3036590103 cites W2007008305 @default.
- W3036590103 cites W2028166238 @default.
- W3036590103 cites W2039708501 @default.
- W3036590103 cites W2048763981 @default.
- W3036590103 cites W2049974290 @default.
- W3036590103 cites W2077008103 @default.
- W3036590103 cites W2083613895 @default.
- W3036590103 cites W2085496778 @default.
- W3036590103 cites W2102871258 @default.
- W3036590103 cites W2120575449 @default.
- W3036590103 cites W2135479785 @default.
- W3036590103 cites W2149167810 @default.
- W3036590103 cites W2156005216 @default.
- W3036590103 cites W2220031198 @default.
- W3036590103 cites W2269075851 @default.
- W3036590103 cites W2498157954 @default.
- W3036590103 cites W2510806995 @default.
- W3036590103 cites W2525748878 @default.
- W3036590103 cites W2573798107 @default.
- W3036590103 cites W2597181770 @default.
- W3036590103 cites W2605147767 @default.
- W3036590103 cites W2616324011 @default.
- W3036590103 cites W2745110207 @default.
- W3036590103 cites W2770250658 @default.
- W3036590103 cites W2788421913 @default.
- W3036590103 cites W2803629276 @default.
- W3036590103 cites W2963292939 @default.
- W3036590103 cites W2963433607 @default.
- W3036590103 cites W2963459284 @default.
- W3036590103 cites W3101260193 @default.
- W3036590103 cites W4230055019 @default.
- W3036590103 cites W4302564868 @default.
- W3036590103 cites W4509327 @default.
- W3036590103 doi "https://doi.org/10.1080/10556788.2020.1775828" @default.
- W3036590103 hasPublicationYear "2020" @default.
- W3036590103 type Work @default.
- W3036590103 sameAs 3036590103 @default.
- W3036590103 citedByCount "1" @default.
- W3036590103 countsByYear W30365901032021 @default.
- W3036590103 crossrefType "journal-article" @default.
- W3036590103 hasAuthorship W3036590103A5005918238 @default.
- W3036590103 hasAuthorship W3036590103A5024258728 @default.
- W3036590103 hasAuthorship W3036590103A5036298459 @default.
- W3036590103 hasAuthorship W3036590103A5090885683 @default.
- W3036590103 hasBestOaLocation W30365901032 @default.
- W3036590103 hasConcept C11413529 @default.
- W3036590103 hasConcept C121332964 @default.
- W3036590103 hasConcept C126255220 @default.
- W3036590103 hasConcept C151730666 @default.
- W3036590103 hasConcept C154945302 @default.
- W3036590103 hasConcept C155512373 @default.
- W3036590103 hasConcept C158622935 @default.
- W3036590103 hasConcept C2779343474 @default.
- W3036590103 hasConcept C33923547 @default.
- W3036590103 hasConcept C41008148 @default.
- W3036590103 hasConcept C50644808 @default.
- W3036590103 hasConcept C62520636 @default.
- W3036590103 hasConcept C86803240 @default.
- W3036590103 hasConceptScore W3036590103C11413529 @default.
- W3036590103 hasConceptScore W3036590103C121332964 @default.
- W3036590103 hasConceptScore W3036590103C126255220 @default.
- W3036590103 hasConceptScore W3036590103C151730666 @default.
- W3036590103 hasConceptScore W3036590103C154945302 @default.
- W3036590103 hasConceptScore W3036590103C155512373 @default.
- W3036590103 hasConceptScore W3036590103C158622935 @default.
- W3036590103 hasConceptScore W3036590103C2779343474 @default.
- W3036590103 hasConceptScore W3036590103C33923547 @default.
- W3036590103 hasConceptScore W3036590103C41008148 @default.
- W3036590103 hasConceptScore W3036590103C50644808 @default.
- W3036590103 hasConceptScore W3036590103C62520636 @default.
- W3036590103 hasConceptScore W3036590103C86803240 @default.
- W3036590103 hasFunder F4320324219 @default.
- W3036590103 hasIssue "1" @default.
- W3036590103 hasLocation W30365901031 @default.
- W3036590103 hasLocation W30365901032 @default.
- W3036590103 hasLocation W30365901033 @default.
- W3036590103 hasLocation W30365901034 @default.
- W3036590103 hasLocation W30365901035 @default.
- W3036590103 hasLocation W30365901036 @default.
- W3036590103 hasOpenAccess W3036590103 @default.
- W3036590103 hasPrimaryLocation W30365901031 @default.
- W3036590103 hasRelatedWork W1986866994 @default.