Matches in SemOpenAlex for { <https://semopenalex.org/work/W2038997435> ?p ?o ?g. }
- W2038997435 endingPage "1079" @default.
- W2038997435 startingPage "1064" @default.
- W2038997435 abstract "The present work deals with one of the major and not yet completely understood topics of supervised connectionist models. Namely, it investigates the relationships between the difficulty of a given learning task and the chosen neural network architecture. These relationships have been investigated and nicely established for some interesting problems in the case of neural networks used for processing vectors and sequences, but only a few studies have dealt with loading problems involving graphical inputs. In this paper, we present sufficient conditions which guarantee the absence of local minima of the error function in the case of learning directed acyclic graphs with recursive neural networks. We introduce topological indices which can be directly calculated from the given training set and that allows us to design the neural architecture with local minima free error function. In particular, we conceive a reduction algorithm that involves both the information attached to the nodes and the topology, which enlarges significantly the class of the problems with unimodal error function previously proposed in the literature." @default.
- W2038997435 created "2016-06-24" @default.
- W2038997435 creator A5022658803 @default.
- W2038997435 creator A5064873591 @default.
- W2038997435 date "2005-10-01" @default.
- W2038997435 modified "2023-10-03" @default.
- W2038997435 title "The loading problem for recursive neural networks" @default.
- W2038997435 cites W1883807 @default.
- W2038997435 cites W196871588 @default.
- W2038997435 cites W2022740958 @default.
- W2038997435 cites W2041768209 @default.
- W2038997435 cites W2046949678 @default.
- W2038997435 cites W2049066061 @default.
- W2038997435 cites W2059024546 @default.
- W2038997435 cites W2078626246 @default.
- W2038997435 cites W2080075452 @default.
- W2038997435 cites W2099617759 @default.
- W2038997435 cites W2104518905 @default.
- W2038997435 cites W2113634576 @default.
- W2038997435 cites W2114160202 @default.
- W2038997435 cites W2116815946 @default.
- W2038997435 cites W2127827747 @default.
- W2038997435 cites W2132539465 @default.
- W2038997435 cites W2135804779 @default.
- W2038997435 cites W2166681504 @default.
- W2038997435 cites W2170589060 @default.
- W2038997435 cites W2171931454 @default.
- W2038997435 doi "https://doi.org/10.1016/j.neunet.2005.07.006" @default.
- W2038997435 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/16198537" @default.
- W2038997435 hasPublicationYear "2005" @default.
- W2038997435 type Work @default.
- W2038997435 sameAs 2038997435 @default.
- W2038997435 citedByCount "5" @default.
- W2038997435 countsByYear W20389974352023 @default.
- W2038997435 crossrefType "journal-article" @default.
- W2038997435 hasAuthorship W2038997435A5022658803 @default.
- W2038997435 hasAuthorship W2038997435A5064873591 @default.
- W2038997435 hasConcept C111335779 @default.
- W2038997435 hasConcept C11413529 @default.
- W2038997435 hasConcept C114614502 @default.
- W2038997435 hasConcept C134306372 @default.
- W2038997435 hasConcept C14036430 @default.
- W2038997435 hasConcept C154945302 @default.
- W2038997435 hasConcept C175202392 @default.
- W2038997435 hasConcept C177264268 @default.
- W2038997435 hasConcept C184720557 @default.
- W2038997435 hasConcept C186633575 @default.
- W2038997435 hasConcept C199360897 @default.
- W2038997435 hasConcept C2524010 @default.
- W2038997435 hasConcept C2777212361 @default.
- W2038997435 hasConcept C33923547 @default.
- W2038997435 hasConcept C41008148 @default.
- W2038997435 hasConcept C50644808 @default.
- W2038997435 hasConcept C78458016 @default.
- W2038997435 hasConcept C80444323 @default.
- W2038997435 hasConcept C8521452 @default.
- W2038997435 hasConcept C86582703 @default.
- W2038997435 hasConcept C86803240 @default.
- W2038997435 hasConceptScore W2038997435C111335779 @default.
- W2038997435 hasConceptScore W2038997435C11413529 @default.
- W2038997435 hasConceptScore W2038997435C114614502 @default.
- W2038997435 hasConceptScore W2038997435C134306372 @default.
- W2038997435 hasConceptScore W2038997435C14036430 @default.
- W2038997435 hasConceptScore W2038997435C154945302 @default.
- W2038997435 hasConceptScore W2038997435C175202392 @default.
- W2038997435 hasConceptScore W2038997435C177264268 @default.
- W2038997435 hasConceptScore W2038997435C184720557 @default.
- W2038997435 hasConceptScore W2038997435C186633575 @default.
- W2038997435 hasConceptScore W2038997435C199360897 @default.
- W2038997435 hasConceptScore W2038997435C2524010 @default.
- W2038997435 hasConceptScore W2038997435C2777212361 @default.
- W2038997435 hasConceptScore W2038997435C33923547 @default.
- W2038997435 hasConceptScore W2038997435C41008148 @default.
- W2038997435 hasConceptScore W2038997435C50644808 @default.
- W2038997435 hasConceptScore W2038997435C78458016 @default.
- W2038997435 hasConceptScore W2038997435C80444323 @default.
- W2038997435 hasConceptScore W2038997435C8521452 @default.
- W2038997435 hasConceptScore W2038997435C86582703 @default.
- W2038997435 hasConceptScore W2038997435C86803240 @default.
- W2038997435 hasIssue "8" @default.
- W2038997435 hasLocation W20389974351 @default.
- W2038997435 hasLocation W20389974352 @default.
- W2038997435 hasOpenAccess W2038997435 @default.
- W2038997435 hasPrimaryLocation W20389974351 @default.
- W2038997435 hasRelatedWork W2132388328 @default.
- W2038997435 hasRelatedWork W2149173727 @default.
- W2038997435 hasRelatedWork W2158599326 @default.
- W2038997435 hasRelatedWork W2386072085 @default.
- W2038997435 hasRelatedWork W2386387936 @default.
- W2038997435 hasRelatedWork W2765937093 @default.
- W2038997435 hasRelatedWork W2950570 @default.
- W2038997435 hasRelatedWork W4309129982 @default.
- W2038997435 hasRelatedWork W2103466658 @default.
- W2038997435 hasRelatedWork W2169830891 @default.
- W2038997435 hasVolume "18" @default.
- W2038997435 isParatext "false" @default.
- W2038997435 isRetracted "false" @default.
- W2038997435 magId "2038997435" @default.