Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996751421> ?p ?o ?g. }
- W2996751421 abstract "Recent results in nonparametric regression show that for deep learning, i.e., for neural network estimates with many hidden layers, we are able to achieve good rates of convergence even in case of high-dimensional predictor variables, provided suitable assumptions on the structure of the regression function are imposed. The estimates are defined by minimizing the empirical $L_2$ risk over a class of neural networks. In practice it is not clear how this can be done exactly. In this article we introduce a new neural network regression estimate where most of the weights are chosen regardless of the data motivated by some recent approximation results for neural networks, and which is therefore easy to implement. We show that for this estimate we can derive rates of convergence results in case the regression function is smooth. We combine this estimate with the projection pursuit, where we choose the directions randomly, and we show that for sufficiently many repititions we get a neural network regression estimate which is easy to implement and which achieves the one-dimensional rate of convergence (up to some logarithmic factor) in case that the regression function satisfies the assumptions of projection pursuit." @default.
- W2996751421 created "2019-12-26" @default.
- W2996751421 creator A5018592252 @default.
- W2996751421 creator A5028420890 @default.
- W2996751421 creator A5046164638 @default.
- W2996751421 date "2019-12-09" @default.
- W2996751421 modified "2023-10-03" @default.
- W2996751421 title "Analysis of the rate of convergence of neural network regression estimates which are easy to implement." @default.
- W2996751421 cites W1484867920 @default.
- W2996751421 cites W1564947197 @default.
- W2996751421 cites W1569512666 @default.
- W2996751421 cites W1969640518 @default.
- W2996751421 cites W1978930761 @default.
- W2996751421 cites W1982029046 @default.
- W2996751421 cites W2018450309 @default.
- W2996751421 cites W2034106324 @default.
- W2996751421 cites W2038845890 @default.
- W2996751421 cites W2053200087 @default.
- W2996751421 cites W2058225082 @default.
- W2996751421 cites W2065274576 @default.
- W2996751421 cites W2076063813 @default.
- W2996751421 cites W2091886411 @default.
- W2996751421 cites W2113239850 @default.
- W2996751421 cites W2117812871 @default.
- W2996751421 cites W2133671888 @default.
- W2996751421 cites W2559431973 @default.
- W2996751421 cites W2751811815 @default.
- W2996751421 cites W2803955134 @default.
- W2996751421 cites W2894972989 @default.
- W2996751421 cites W2946302218 @default.
- W2996751421 cites W2962930448 @default.
- W2996751421 cites W2963264710 @default.
- W2996751421 cites W2963446085 @default.
- W2996751421 cites W2963744427 @default.
- W2996751421 cites W2970175428 @default.
- W2996751421 cites W2970769658 @default.
- W2996751421 cites W2993367001 @default.
- W2996751421 cites W2993629754 @default.
- W2996751421 cites W3099812441 @default.
- W2996751421 cites W3101636142 @default.
- W2996751421 cites W3102511045 @default.
- W2996751421 hasPublicationYear "2019" @default.
- W2996751421 type Work @default.
- W2996751421 sameAs 2996751421 @default.
- W2996751421 citedByCount "1" @default.
- W2996751421 countsByYear W29967514212021 @default.
- W2996751421 crossrefType "posted-content" @default.
- W2996751421 hasAuthorship W2996751421A5018592252 @default.
- W2996751421 hasAuthorship W2996751421A5028420890 @default.
- W2996751421 hasAuthorship W2996751421A5046164638 @default.
- W2996751421 hasConcept C102366305 @default.
- W2996751421 hasConcept C105795698 @default.
- W2996751421 hasConcept C11413529 @default.
- W2996751421 hasConcept C118038509 @default.
- W2996751421 hasConcept C119857082 @default.
- W2996751421 hasConcept C127162648 @default.
- W2996751421 hasConcept C134306372 @default.
- W2996751421 hasConcept C14036430 @default.
- W2996751421 hasConcept C149782125 @default.
- W2996751421 hasConcept C152877465 @default.
- W2996751421 hasConcept C154945302 @default.
- W2996751421 hasConcept C162324750 @default.
- W2996751421 hasConcept C2777303404 @default.
- W2996751421 hasConcept C31258907 @default.
- W2996751421 hasConcept C33923547 @default.
- W2996751421 hasConcept C39927690 @default.
- W2996751421 hasConcept C41008148 @default.
- W2996751421 hasConcept C50522688 @default.
- W2996751421 hasConcept C50644808 @default.
- W2996751421 hasConcept C57493831 @default.
- W2996751421 hasConcept C57869625 @default.
- W2996751421 hasConcept C74127309 @default.
- W2996751421 hasConcept C78458016 @default.
- W2996751421 hasConcept C83546350 @default.
- W2996751421 hasConcept C86803240 @default.
- W2996751421 hasConceptScore W2996751421C102366305 @default.
- W2996751421 hasConceptScore W2996751421C105795698 @default.
- W2996751421 hasConceptScore W2996751421C11413529 @default.
- W2996751421 hasConceptScore W2996751421C118038509 @default.
- W2996751421 hasConceptScore W2996751421C119857082 @default.
- W2996751421 hasConceptScore W2996751421C127162648 @default.
- W2996751421 hasConceptScore W2996751421C134306372 @default.
- W2996751421 hasConceptScore W2996751421C14036430 @default.
- W2996751421 hasConceptScore W2996751421C149782125 @default.
- W2996751421 hasConceptScore W2996751421C152877465 @default.
- W2996751421 hasConceptScore W2996751421C154945302 @default.
- W2996751421 hasConceptScore W2996751421C162324750 @default.
- W2996751421 hasConceptScore W2996751421C2777303404 @default.
- W2996751421 hasConceptScore W2996751421C31258907 @default.
- W2996751421 hasConceptScore W2996751421C33923547 @default.
- W2996751421 hasConceptScore W2996751421C39927690 @default.
- W2996751421 hasConceptScore W2996751421C41008148 @default.
- W2996751421 hasConceptScore W2996751421C50522688 @default.
- W2996751421 hasConceptScore W2996751421C50644808 @default.
- W2996751421 hasConceptScore W2996751421C57493831 @default.
- W2996751421 hasConceptScore W2996751421C57869625 @default.
- W2996751421 hasConceptScore W2996751421C74127309 @default.
- W2996751421 hasConceptScore W2996751421C78458016 @default.
- W2996751421 hasConceptScore W2996751421C83546350 @default.
- W2996751421 hasConceptScore W2996751421C86803240 @default.