Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035281012> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3035281012 endingPage "4042" @default.
- W3035281012 startingPage "4032" @default.
- W3035281012 abstract "Deep neural networks (DNNs) achieve impressive results for complicated tasks like object detection on images and speech recognition. Motivated by this practical success, there is now a strong interest in showing good theoretical properties of DNNs. To describe for which tasks DNNs perform well and when they fail, it is a key challenge to understand their performance. The aim of this paper is to contribute to the current statistical theory of DNNs. We apply DNNs on high dimensional data and we show that the least squares regression estimates using DNNs are able to achieve dimensionality reduction in case that the regression function has locally low dimensionality. Consequently, the rate of convergence of the estimate does not depend on its input dimension <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$d$ </tex-math></inline-formula> , but on its local dimension <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$d^{*}$ </tex-math></inline-formula> and the DNNs are able to circumvent the curse of dimensionality in case that <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$d^{*}$ </tex-math></inline-formula> is much smaller than <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$d$ </tex-math></inline-formula> . In our simulation study we provide numerical experiments to support our theoretical result and we compare our estimate with other conventional nonparametric regression estimates. The performance of our estimates is also validated in experiments with real data." @default.
- W3035281012 created "2020-06-19" @default.
- W3035281012 creator A5024305086 @default.
- W3035281012 creator A5028420890 @default.
- W3035281012 creator A5046164638 @default.
- W3035281012 date "2022-06-01" @default.
- W3035281012 modified "2023-10-03" @default.
- W3035281012 title "Estimation of a Function of Low Local Dimensionality by Deep Neural Networks" @default.
- W3035281012 cites W1484867920 @default.
- W3035281012 cites W1524622012 @default.
- W3035281012 cites W1564947197 @default.
- W3035281012 cites W1680677650 @default.
- W3035281012 cites W2001141328 @default.
- W3035281012 cites W2006398000 @default.
- W3035281012 cites W2034106324 @default.
- W3035281012 cites W2038845890 @default.
- W3035281012 cites W2069016826 @default.
- W3035281012 cites W2076063813 @default.
- W3035281012 cites W2097308346 @default.
- W3035281012 cites W2129586496 @default.
- W3035281012 cites W2137234026 @default.
- W3035281012 cites W2559431973 @default.
- W3035281012 cites W2946302218 @default.
- W3035281012 cites W2963273475 @default.
- W3035281012 cites W3102511045 @default.
- W3035281012 cites W3190727821 @default.
- W3035281012 cites W3201938571 @default.
- W3035281012 doi "https://doi.org/10.1109/tit.2022.3146620" @default.
- W3035281012 hasPublicationYear "2022" @default.
- W3035281012 type Work @default.
- W3035281012 sameAs 3035281012 @default.
- W3035281012 citedByCount "11" @default.
- W3035281012 countsByYear W30352810122019 @default.
- W3035281012 countsByYear W30352810122020 @default.
- W3035281012 countsByYear W30352810122021 @default.
- W3035281012 countsByYear W30352810122023 @default.
- W3035281012 crossrefType "journal-article" @default.
- W3035281012 hasAuthorship W3035281012A5024305086 @default.
- W3035281012 hasAuthorship W3035281012A5028420890 @default.
- W3035281012 hasAuthorship W3035281012A5046164638 @default.
- W3035281012 hasBestOaLocation W30352810122 @default.
- W3035281012 hasConcept C111030470 @default.
- W3035281012 hasConcept C11413529 @default.
- W3035281012 hasConcept C114614502 @default.
- W3035281012 hasConcept C118615104 @default.
- W3035281012 hasConcept C14036430 @default.
- W3035281012 hasConcept C154945302 @default.
- W3035281012 hasConcept C33676613 @default.
- W3035281012 hasConcept C33923547 @default.
- W3035281012 hasConcept C41008148 @default.
- W3035281012 hasConcept C45357846 @default.
- W3035281012 hasConcept C50644808 @default.
- W3035281012 hasConcept C70518039 @default.
- W3035281012 hasConcept C78458016 @default.
- W3035281012 hasConcept C80444323 @default.
- W3035281012 hasConcept C86803240 @default.
- W3035281012 hasConcept C94375191 @default.
- W3035281012 hasConceptScore W3035281012C111030470 @default.
- W3035281012 hasConceptScore W3035281012C11413529 @default.
- W3035281012 hasConceptScore W3035281012C114614502 @default.
- W3035281012 hasConceptScore W3035281012C118615104 @default.
- W3035281012 hasConceptScore W3035281012C14036430 @default.
- W3035281012 hasConceptScore W3035281012C154945302 @default.
- W3035281012 hasConceptScore W3035281012C33676613 @default.
- W3035281012 hasConceptScore W3035281012C33923547 @default.
- W3035281012 hasConceptScore W3035281012C41008148 @default.
- W3035281012 hasConceptScore W3035281012C45357846 @default.
- W3035281012 hasConceptScore W3035281012C50644808 @default.
- W3035281012 hasConceptScore W3035281012C70518039 @default.
- W3035281012 hasConceptScore W3035281012C78458016 @default.
- W3035281012 hasConceptScore W3035281012C80444323 @default.
- W3035281012 hasConceptScore W3035281012C86803240 @default.
- W3035281012 hasConceptScore W3035281012C94375191 @default.
- W3035281012 hasFunder F4320320879 @default.
- W3035281012 hasFunder F4320334593 @default.
- W3035281012 hasIssue "6" @default.
- W3035281012 hasLocation W30352810121 @default.
- W3035281012 hasLocation W30352810122 @default.
- W3035281012 hasLocation W30352810123 @default.
- W3035281012 hasOpenAccess W3035281012 @default.
- W3035281012 hasPrimaryLocation W30352810121 @default.
- W3035281012 hasRelatedWork W1552543208 @default.
- W3035281012 hasRelatedWork W1607154928 @default.
- W3035281012 hasRelatedWork W1995622179 @default.
- W3035281012 hasRelatedWork W2319450352 @default.
- W3035281012 hasRelatedWork W3122240332 @default.
- W3035281012 hasRelatedWork W398889120 @default.
- W3035281012 hasRelatedWork W4281553196 @default.
- W3035281012 hasRelatedWork W4285787138 @default.
- W3035281012 hasRelatedWork W4293087755 @default.
- W3035281012 hasRelatedWork W4313283835 @default.
- W3035281012 hasVolume "68" @default.
- W3035281012 isParatext "false" @default.
- W3035281012 isRetracted "false" @default.
- W3035281012 magId "3035281012" @default.
- W3035281012 workType "article" @default.