Matches in SemOpenAlex for { <https://semopenalex.org/work/W2000354444> ?p ?o ?g. }
- W2000354444 endingPage "3408" @default.
- W2000354444 startingPage "3387" @default.
- W2000354444 abstract "In this paper we prove that any affine function defined on a d-simplex in Rd can be uniformly approximated by a single-layer neural network having only two neurons irrespective of d. The weights of this network are obtained in a closed analytical form, without training. This fact gives a correspondence rule that allows to transform mathematical approximants based on piecewise affine functions, into neural networks. We introduce such an approximant, adaptive splitting based on cubature (ASBC), for the efficient approximation of continuous functions. Using ASBC and the above correspondence rule, we obtain a neural tree. Numerical experiments on learning the function distance from a variable point to a geometric body in two and three dimensions show fast learning speed and high accuracy when compared with single-hidden layer feedforward networks trained by a trust region method based on the interior-reflective Newton algorithm." @default.
- W2000354444 created "2016-06-24" @default.
- W2000354444 creator A5067073804 @default.
- W2000354444 creator A5089116457 @default.
- W2000354444 date "2008-10-01" @default.
- W2000354444 modified "2023-10-03" @default.
- W2000354444 title "Fast training of neural trees by adaptive splitting based on cubature" @default.
- W2000354444 cites W1498393493 @default.
- W2000354444 cites W1514292813 @default.
- W2000354444 cites W1538954065 @default.
- W2000354444 cites W1550780726 @default.
- W2000354444 cites W1815731809 @default.
- W2000354444 cites W1964199832 @default.
- W2000354444 cites W1966895140 @default.
- W2000354444 cites W1967646346 @default.
- W2000354444 cites W1973513227 @default.
- W2000354444 cites W1973705782 @default.
- W2000354444 cites W1990781410 @default.
- W2000354444 cites W1995501836 @default.
- W2000354444 cites W2003512260 @default.
- W2000354444 cites W2006240266 @default.
- W2000354444 cites W2009566405 @default.
- W2000354444 cites W2017050618 @default.
- W2000354444 cites W2019022049 @default.
- W2000354444 cites W2021311647 @default.
- W2000354444 cites W2025653905 @default.
- W2000354444 cites W2036796788 @default.
- W2000354444 cites W2048838384 @default.
- W2000354444 cites W2051668038 @default.
- W2000354444 cites W2053350517 @default.
- W2000354444 cites W2054002339 @default.
- W2000354444 cites W2057667075 @default.
- W2000354444 cites W2062430377 @default.
- W2000354444 cites W2071467620 @default.
- W2000354444 cites W2082131680 @default.
- W2000354444 cites W2089455490 @default.
- W2000354444 cites W2090105210 @default.
- W2000354444 cites W2091772836 @default.
- W2000354444 cites W2110158084 @default.
- W2000354444 cites W2111072639 @default.
- W2000354444 cites W2124290836 @default.
- W2000354444 cites W2145726976 @default.
- W2000354444 cites W2149444585 @default.
- W2000354444 cites W2150884987 @default.
- W2000354444 cites W2169976759 @default.
- W2000354444 cites W227905838 @default.
- W2000354444 cites W3120055268 @default.
- W2000354444 cites W574552420 @default.
- W2000354444 doi "https://doi.org/10.1016/j.neucom.2007.12.001" @default.
- W2000354444 hasPublicationYear "2008" @default.
- W2000354444 type Work @default.
- W2000354444 sameAs 2000354444 @default.
- W2000354444 citedByCount "4" @default.
- W2000354444 crossrefType "journal-article" @default.
- W2000354444 hasAuthorship W2000354444A5067073804 @default.
- W2000354444 hasAuthorship W2000354444A5089116457 @default.
- W2000354444 hasConcept C11413529 @default.
- W2000354444 hasConcept C134306372 @default.
- W2000354444 hasConcept C14036430 @default.
- W2000354444 hasConcept C154945302 @default.
- W2000354444 hasConcept C164660894 @default.
- W2000354444 hasConcept C2524010 @default.
- W2000354444 hasConcept C28719098 @default.
- W2000354444 hasConcept C33923547 @default.
- W2000354444 hasConcept C41008148 @default.
- W2000354444 hasConcept C47702885 @default.
- W2000354444 hasConcept C50644808 @default.
- W2000354444 hasConcept C62438384 @default.
- W2000354444 hasConcept C78458016 @default.
- W2000354444 hasConcept C86803240 @default.
- W2000354444 hasConcept C92757383 @default.
- W2000354444 hasConceptScore W2000354444C11413529 @default.
- W2000354444 hasConceptScore W2000354444C134306372 @default.
- W2000354444 hasConceptScore W2000354444C14036430 @default.
- W2000354444 hasConceptScore W2000354444C154945302 @default.
- W2000354444 hasConceptScore W2000354444C164660894 @default.
- W2000354444 hasConceptScore W2000354444C2524010 @default.
- W2000354444 hasConceptScore W2000354444C28719098 @default.
- W2000354444 hasConceptScore W2000354444C33923547 @default.
- W2000354444 hasConceptScore W2000354444C41008148 @default.
- W2000354444 hasConceptScore W2000354444C47702885 @default.
- W2000354444 hasConceptScore W2000354444C50644808 @default.
- W2000354444 hasConceptScore W2000354444C62438384 @default.
- W2000354444 hasConceptScore W2000354444C78458016 @default.
- W2000354444 hasConceptScore W2000354444C86803240 @default.
- W2000354444 hasConceptScore W2000354444C92757383 @default.
- W2000354444 hasIssue "16-18" @default.
- W2000354444 hasLocation W20003544441 @default.
- W2000354444 hasOpenAccess W2000354444 @default.
- W2000354444 hasPrimaryLocation W20003544441 @default.
- W2000354444 hasRelatedWork W1986370213 @default.
- W2000354444 hasRelatedWork W2000354444 @default.
- W2000354444 hasRelatedWork W2075328869 @default.
- W2000354444 hasRelatedWork W2109836114 @default.
- W2000354444 hasRelatedWork W2360829920 @default.
- W2000354444 hasRelatedWork W2380471201 @default.
- W2000354444 hasRelatedWork W2391384657 @default.
- W2000354444 hasRelatedWork W2392110728 @default.