Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313389306> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4313389306 endingPage "217" @default.
- W4313389306 startingPage "217" @default.
- W4313389306 abstract "A large number of researchers spend a lot of time searching for the most efficient neural network to solve a given problem. The procedure of configuration, training, testing, and comparison for expected performance is applied to each experimental neural network. The configuration parameters—training methods, transfer functions, number of hidden layers, number of neurons, number of epochs, and tolerable error—have multiple possible values. Setting guidelines for appropriate parameter values would shorten the time required to create an efficient neural network, facilitate researchers, and provide a tool to improve the performance of automated neural network search methods. The task considered in this paper is related to the determination of upper bounds for the number of hidden layers and the number of neurons in them for approximating artificial neural networks trained with algorithms using the Jacobi matrix in the error function. The derived formulas for the upper limits of the number of hidden layers and the number of neurons in them are proved theoretically, and the presented experiments confirm their validity. They show that the search for an efficient neural network can focus below certain upper bounds, and above them, it becomes pointless. The formulas provide researchers with a useful auxiliary tool in the search for efficient neural networks with optimal topology. They are applicable to neural networks trained with methods such as Levenberg–Marquardt, Gauss–Newton, Bayesian regularization, scaled conjugate gradient, BFGS quasi-Newton, etc., which use the Jacobi matrix." @default.
- W4313389306 created "2023-01-06" @default.
- W4313389306 creator A5028390927 @default.
- W4313389306 creator A5072132291 @default.
- W4313389306 creator A5076817274 @default.
- W4313389306 creator A5080747622 @default.
- W4313389306 date "2023-01-01" @default.
- W4313389306 modified "2023-09-26" @default.
- W4313389306 title "Finding the Optimal Topology of an Approximating Neural Network" @default.
- W4313389306 cites W1596746635 @default.
- W4313389306 cites W1993589255 @default.
- W4313389306 cites W2059585936 @default.
- W4313389306 cites W2070188654 @default.
- W4313389306 cites W2070467542 @default.
- W4313389306 cites W2085369498 @default.
- W4313389306 cites W2104714048 @default.
- W4313389306 cites W2125818553 @default.
- W4313389306 cites W2137356002 @default.
- W4313389306 cites W2137977791 @default.
- W4313389306 cites W2171673774 @default.
- W4313389306 cites W2204165371 @default.
- W4313389306 cites W2512378354 @default.
- W4313389306 cites W2512949072 @default.
- W4313389306 cites W2517822188 @default.
- W4313389306 cites W2747971139 @default.
- W4313389306 cites W2769912520 @default.
- W4313389306 cites W2911355096 @default.
- W4313389306 cites W2945740093 @default.
- W4313389306 cites W3110332970 @default.
- W4313389306 cites W3152845623 @default.
- W4313389306 cites W3215894900 @default.
- W4313389306 cites W92617545 @default.
- W4313389306 cites W2104490646 @default.
- W4313389306 doi "https://doi.org/10.3390/math11010217" @default.
- W4313389306 hasPublicationYear "2023" @default.
- W4313389306 type Work @default.
- W4313389306 citedByCount "2" @default.
- W4313389306 countsByYear W43133893062023 @default.
- W4313389306 crossrefType "journal-article" @default.
- W4313389306 hasAuthorship W4313389306A5028390927 @default.
- W4313389306 hasAuthorship W4313389306A5072132291 @default.
- W4313389306 hasAuthorship W4313389306A5076817274 @default.
- W4313389306 hasAuthorship W4313389306A5080747622 @default.
- W4313389306 hasBestOaLocation W43133893061 @default.
- W4313389306 hasConcept C11413529 @default.
- W4313389306 hasConcept C114614502 @default.
- W4313389306 hasConcept C132721684 @default.
- W4313389306 hasConcept C151319957 @default.
- W4313389306 hasConcept C154945302 @default.
- W4313389306 hasConcept C175202392 @default.
- W4313389306 hasConcept C184720557 @default.
- W4313389306 hasConcept C200331156 @default.
- W4313389306 hasConcept C28826006 @default.
- W4313389306 hasConcept C31258907 @default.
- W4313389306 hasConcept C33923547 @default.
- W4313389306 hasConcept C41008148 @default.
- W4313389306 hasConcept C50644808 @default.
- W4313389306 hasConcept C81184566 @default.
- W4313389306 hasConcept C86582703 @default.
- W4313389306 hasConceptScore W4313389306C11413529 @default.
- W4313389306 hasConceptScore W4313389306C114614502 @default.
- W4313389306 hasConceptScore W4313389306C132721684 @default.
- W4313389306 hasConceptScore W4313389306C151319957 @default.
- W4313389306 hasConceptScore W4313389306C154945302 @default.
- W4313389306 hasConceptScore W4313389306C175202392 @default.
- W4313389306 hasConceptScore W4313389306C184720557 @default.
- W4313389306 hasConceptScore W4313389306C200331156 @default.
- W4313389306 hasConceptScore W4313389306C28826006 @default.
- W4313389306 hasConceptScore W4313389306C31258907 @default.
- W4313389306 hasConceptScore W4313389306C33923547 @default.
- W4313389306 hasConceptScore W4313389306C41008148 @default.
- W4313389306 hasConceptScore W4313389306C50644808 @default.
- W4313389306 hasConceptScore W4313389306C81184566 @default.
- W4313389306 hasConceptScore W4313389306C86582703 @default.
- W4313389306 hasIssue "1" @default.
- W4313389306 hasLocation W43133893061 @default.
- W4313389306 hasLocation W43133893062 @default.
- W4313389306 hasOpenAccess W4313389306 @default.
- W4313389306 hasPrimaryLocation W43133893061 @default.
- W4313389306 hasRelatedWork W1536970676 @default.
- W4313389306 hasRelatedWork W1584270863 @default.
- W4313389306 hasRelatedWork W1595652908 @default.
- W4313389306 hasRelatedWork W1963768346 @default.
- W4313389306 hasRelatedWork W2059808679 @default.
- W4313389306 hasRelatedWork W2085961337 @default.
- W4313389306 hasRelatedWork W2367207292 @default.
- W4313389306 hasRelatedWork W2386387936 @default.
- W4313389306 hasRelatedWork W4313389306 @default.
- W4313389306 hasRelatedWork W651238688 @default.
- W4313389306 hasVolume "11" @default.
- W4313389306 isParatext "false" @default.
- W4313389306 isRetracted "false" @default.
- W4313389306 workType "article" @default.