FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133651710> ?p ?o ?g. }

• W3133651710 endingPage "101746" @default.
• W3133651710 startingPage "101746" @default.
• W3133651710 abstract "Artificial neural networks (ANNs) have become a very powerful tool in the approximation of high-dimensional functions. Especially, deep ANNs, consisting of a large number of hidden layers, have been very successfully used in a series of practical relevant computational problems involving high-dimensional input data ranging from classification tasks in supervised learning to optimal decision problems in reinforcement learning. There are also a number of mathematical results in the scientific literature which study the approximation capacities of ANNs in the context of high-dimensional target functions. In particular, there are a series of mathematical results in the scientific literature which show that sufficiently deep ANNs have the capacity to overcome the curse of dimensionality in the approximation of certain target function classes in the sense that the number of parameters of the approximating ANNs grows at most polynomially in the dimension d∈N of the target functions under considerations. In the proofs of several of such high-dimensional approximation results it is crucial that the involved ANNs are sufficiently deep and consist a sufficiently large number of hidden layers which grows in the dimension of the considered target functions. It is the topic of this work to look a bit more detailed to the deepness of the involved ANNs in the approximation of high-dimensional target functions. In particular, the main result of this work proves that there exists a concretely specified sequence of functions which can be approximated without the curse of dimensionality by sufficiently deep ANNs but which cannot be approximated without the curse of dimensionality if the involved ANNs are shallow or not deep enough." @default.
• W3133651710 created "2021-03-15" @default.
• W3133651710 creator A5009111461 @default.
• W3133651710 creator A5009721579 @default.
• W3133651710 creator A5023888160 @default.
• W3133651710 creator A5074382323 @default.
• W3133651710 date "2023-08-01" @default.
• W3133651710 modified "2023-10-17" @default.
• W3133651710 title "Lower bounds for artificial neural network approximations: A proof that shallow neural networks fail to overcome the curse of dimensionality" @default.
• W3133651710 cites W1971735090 @default.
• W3133651710 cites W1979554434 @default.
• W3133651710 cites W1988115241 @default.
• W3133651710 cites W1994108380 @default.
• W3133651710 cites W2034551836 @default.
• W3133651710 cites W2044828368 @default.
• W3133651710 cites W2074381721 @default.
• W3133651710 cites W2085310530 @default.
• W3133651710 cites W2089947415 @default.
• W3133651710 cites W2099706683 @default.
• W3133651710 cites W2103496339 @default.
• W3133651710 cites W2113990981 @default.
• W3133651710 cites W2137983211 @default.
• W3133651710 cites W2152593035 @default.
• W3133651710 cites W2153714959 @default.
• W3133651710 cites W2158581396 @default.
• W3133651710 cites W2166116275 @default.
• W3133651710 cites W2528305538 @default.
• W3133651710 cites W2747971139 @default.
• W3133651710 cites W2803636134 @default.
• W3133651710 cites W2885273747 @default.
• W3133651710 cites W2890291741 @default.
• W3133651710 cites W2962761333 @default.
• W3133651710 cites W2963146412 @default.
• W3133651710 cites W2967394275 @default.
• W3133651710 cites W2977465327 @default.
• W3133651710 cites W2991444716 @default.
• W3133651710 cites W2995438359 @default.
• W3133651710 cites W3082030075 @default.
• W3133651710 cites W3104183394 @default.
• W3133651710 cites W3115761617 @default.
• W3133651710 cites W3125537303 @default.
• W3133651710 cites W3180808552 @default.
• W3133651710 cites W4234067117 @default.
• W3133651710 cites W4236966694 @default.
• W3133651710 cites W4246262524 @default.
• W3133651710 doi "https://doi.org/10.1016/j.jco.2023.101746" @default.
• W3133651710 hasPublicationYear "2023" @default.
• W3133651710 type Work @default.
• W3133651710 sameAs 3133651710 @default.
• W3133651710 citedByCount "2" @default.
• W3133651710 countsByYear W31336517102023 @default.
• W3133651710 crossrefType "journal-article" @default.
• W3133651710 hasAuthorship W3133651710A5009111461 @default.
• W3133651710 hasAuthorship W3133651710A5009721579 @default.
• W3133651710 hasAuthorship W3133651710A5023888160 @default.
• W3133651710 hasAuthorship W3133651710A5074382323 @default.
• W3133651710 hasBestOaLocation W31336517102 @default.
• W3133651710 hasConcept C108583219 @default.
• W3133651710 hasConcept C108710211 @default.
• W3133651710 hasConcept C111030470 @default.
• W3133651710 hasConcept C119857082 @default.
• W3133651710 hasConcept C126255220 @default.
• W3133651710 hasConcept C143724316 @default.
• W3133651710 hasConcept C151730666 @default.
• W3133651710 hasConcept C154945302 @default.
• W3133651710 hasConcept C202444582 @default.
• W3133651710 hasConcept C2524010 @default.
• W3133651710 hasConcept C2779343474 @default.
• W3133651710 hasConcept C28826006 @default.
• W3133651710 hasConcept C33676613 @default.
• W3133651710 hasConcept C33923547 @default.
• W3133651710 hasConcept C41008148 @default.
• W3133651710 hasConcept C50644808 @default.
• W3133651710 hasConcept C86803240 @default.
• W3133651710 hasConcept C91873725 @default.
• W3133651710 hasConceptScore W3133651710C108583219 @default.
• W3133651710 hasConceptScore W3133651710C108710211 @default.
• W3133651710 hasConceptScore W3133651710C111030470 @default.
• W3133651710 hasConceptScore W3133651710C119857082 @default.
• W3133651710 hasConceptScore W3133651710C126255220 @default.
• W3133651710 hasConceptScore W3133651710C143724316 @default.
• W3133651710 hasConceptScore W3133651710C151730666 @default.
• W3133651710 hasConceptScore W3133651710C154945302 @default.
• W3133651710 hasConceptScore W3133651710C202444582 @default.
• W3133651710 hasConceptScore W3133651710C2524010 @default.
• W3133651710 hasConceptScore W3133651710C2779343474 @default.
• W3133651710 hasConceptScore W3133651710C28826006 @default.
• W3133651710 hasConceptScore W3133651710C33676613 @default.
• W3133651710 hasConceptScore W3133651710C33923547 @default.
• W3133651710 hasConceptScore W3133651710C41008148 @default.
• W3133651710 hasConceptScore W3133651710C50644808 @default.
• W3133651710 hasConceptScore W3133651710C86803240 @default.
• W3133651710 hasConceptScore W3133651710C91873725 @default.
• W3133651710 hasFunder F4320320879 @default.
• W3133651710 hasFunder F4320321181 @default.
• W3133651710 hasFunder F4320331102 @default.
• W3133651710 hasLocation W31336517101 @default.
• W3133651710 hasLocation W31336517102 @default.

• next