Matches in SemOpenAlex for { <https://semopenalex.org/work/W2047962774> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2047962774 endingPage "5464" @default.
- W2047962774 startingPage "5461" @default.
- W2047962774 abstract "Natural gradient descent is an on-line variable-metric optimization algorithm which utilizes an underlying Riemannian parameter space. We analyze the dynamics of natural gradient descent beyond the asymptotic regime by employing an exact statistical mechanics description of learning in two-layer feed-forward neural networks. For a realizable learning scenario we find significant improvements over standard gradient descent for both the transient and asymptotic stages of learning, with a slower power law increase in learning time as task complexity grows." @default.
- W2047962774 created "2016-06-24" @default.
- W2047962774 creator A5023995814 @default.
- W2047962774 creator A5055812530 @default.
- W2047962774 creator A5081568136 @default.
- W2047962774 date "1998-12-14" @default.
- W2047962774 modified "2023-10-16" @default.
- W2047962774 title "Natural Gradient Descent for On-Line Learning" @default.
- W2047962774 cites W1969891152 @default.
- W2047962774 cites W1970789124 @default.
- W2047962774 cites W1995842804 @default.
- W2047962774 cites W2013773819 @default.
- W2047962774 cites W2042318263 @default.
- W2047962774 cites W2079782346 @default.
- W2047962774 cites W2103496339 @default.
- W2047962774 cites W2138157861 @default.
- W2047962774 doi "https://doi.org/10.1103/physrevlett.81.5461" @default.
- W2047962774 hasPublicationYear "1998" @default.
- W2047962774 type Work @default.
- W2047962774 sameAs 2047962774 @default.
- W2047962774 citedByCount "87" @default.
- W2047962774 countsByYear W20479627742012 @default.
- W2047962774 countsByYear W20479627742013 @default.
- W2047962774 countsByYear W20479627742014 @default.
- W2047962774 countsByYear W20479627742015 @default.
- W2047962774 countsByYear W20479627742016 @default.
- W2047962774 countsByYear W20479627742017 @default.
- W2047962774 countsByYear W20479627742018 @default.
- W2047962774 countsByYear W20479627742019 @default.
- W2047962774 countsByYear W20479627742020 @default.
- W2047962774 countsByYear W20479627742021 @default.
- W2047962774 countsByYear W20479627742022 @default.
- W2047962774 countsByYear W20479627742023 @default.
- W2047962774 crossrefType "journal-article" @default.
- W2047962774 hasAuthorship W2047962774A5023995814 @default.
- W2047962774 hasAuthorship W2047962774A5055812530 @default.
- W2047962774 hasAuthorship W2047962774A5081568136 @default.
- W2047962774 hasConcept C121332964 @default.
- W2047962774 hasConcept C121864883 @default.
- W2047962774 hasConcept C134306372 @default.
- W2047962774 hasConcept C153258448 @default.
- W2047962774 hasConcept C154945302 @default.
- W2047962774 hasConcept C162324750 @default.
- W2047962774 hasConcept C167879884 @default.
- W2047962774 hasConcept C176217482 @default.
- W2047962774 hasConcept C198352243 @default.
- W2047962774 hasConcept C206688291 @default.
- W2047962774 hasConcept C21547014 @default.
- W2047962774 hasConcept C2524010 @default.
- W2047962774 hasConcept C28826006 @default.
- W2047962774 hasConcept C33923547 @default.
- W2047962774 hasConcept C41008148 @default.
- W2047962774 hasConcept C50644808 @default.
- W2047962774 hasConceptScore W2047962774C121332964 @default.
- W2047962774 hasConceptScore W2047962774C121864883 @default.
- W2047962774 hasConceptScore W2047962774C134306372 @default.
- W2047962774 hasConceptScore W2047962774C153258448 @default.
- W2047962774 hasConceptScore W2047962774C154945302 @default.
- W2047962774 hasConceptScore W2047962774C162324750 @default.
- W2047962774 hasConceptScore W2047962774C167879884 @default.
- W2047962774 hasConceptScore W2047962774C176217482 @default.
- W2047962774 hasConceptScore W2047962774C198352243 @default.
- W2047962774 hasConceptScore W2047962774C206688291 @default.
- W2047962774 hasConceptScore W2047962774C21547014 @default.
- W2047962774 hasConceptScore W2047962774C2524010 @default.
- W2047962774 hasConceptScore W2047962774C28826006 @default.
- W2047962774 hasConceptScore W2047962774C33923547 @default.
- W2047962774 hasConceptScore W2047962774C41008148 @default.
- W2047962774 hasConceptScore W2047962774C50644808 @default.
- W2047962774 hasIssue "24" @default.
- W2047962774 hasLocation W20479627741 @default.
- W2047962774 hasOpenAccess W2047962774 @default.
- W2047962774 hasPrimaryLocation W20479627741 @default.
- W2047962774 hasRelatedWork W2966383753 @default.
- W2047962774 hasRelatedWork W2998950521 @default.
- W2047962774 hasRelatedWork W3156808687 @default.
- W2047962774 hasRelatedWork W3192094705 @default.
- W2047962774 hasRelatedWork W3215268866 @default.
- W2047962774 hasRelatedWork W4224998919 @default.
- W2047962774 hasRelatedWork W4287028882 @default.
- W2047962774 hasRelatedWork W4288267668 @default.
- W2047962774 hasRelatedWork W4307481289 @default.
- W2047962774 hasRelatedWork W4380358855 @default.
- W2047962774 hasVolume "81" @default.
- W2047962774 isParatext "false" @default.
- W2047962774 isRetracted "false" @default.
- W2047962774 magId "2047962774" @default.
- W2047962774 workType "article" @default.