Matches in SemOpenAlex for { <https://semopenalex.org/work/W1590749351> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W1590749351 abstract "The value of the output function gradient of a neural network, calculated in the training points, plays an essential role for its generalization capability.In this paper a feed forward neural architecture (αNet) that can learn the activation function of its hidden units during the training phase is presented. The automatic learning is obtained through the joint use of the Hermite regression formula and the CGD optimization algorithm with the Powell restart conditions. This technique leads to a smooth output function of αNet in the nearby of the training points, achieving an improvement of the generalization capability and the flexibility of the neural architecture.Experimental results, obtained comparing αNet with traditional architectures with sigmoidal or sinusoidal activation functions, show that the former is very flexible and has good approximation and classification capabilities." @default.
- W1590749351 created "2016-06-24" @default.
- W1590749351 creator A5042079595 @default.
- W1590749351 creator A5046377602 @default.
- W1590749351 creator A5061605283 @default.
- W1590749351 creator A5088723808 @default.
- W1590749351 date "2000-01-01" @default.
- W1590749351 modified "2023-09-24" @default.
- W1590749351 title "Using the Hermite Regression Formula to Design a Neural Architecture with Automatic Learning of the “Hidden” Activation Functions" @default.
- W1590749351 cites W2009323003 @default.
- W1590749351 cites W2010210853 @default.
- W1590749351 cites W2043382734 @default.
- W1590749351 cites W2137983211 @default.
- W1590749351 cites W2169359910 @default.
- W1590749351 cites W242367498 @default.
- W1590749351 cites W2993421702 @default.
- W1590749351 cites W4240861491 @default.
- W1590749351 doi "https://doi.org/10.1007/3-540-46238-4_20" @default.
- W1590749351 hasPublicationYear "2000" @default.
- W1590749351 type Work @default.
- W1590749351 sameAs 1590749351 @default.
- W1590749351 citedByCount "9" @default.
- W1590749351 countsByYear W15907493512012 @default.
- W1590749351 countsByYear W15907493512013 @default.
- W1590749351 countsByYear W15907493512021 @default.
- W1590749351 crossrefType "book-chapter" @default.
- W1590749351 hasAuthorship W1590749351A5042079595 @default.
- W1590749351 hasAuthorship W1590749351A5046377602 @default.
- W1590749351 hasAuthorship W1590749351A5061605283 @default.
- W1590749351 hasAuthorship W1590749351A5088723808 @default.
- W1590749351 hasConcept C105795698 @default.
- W1590749351 hasConcept C11413529 @default.
- W1590749351 hasConcept C126255220 @default.
- W1590749351 hasConcept C134306372 @default.
- W1590749351 hasConcept C14036430 @default.
- W1590749351 hasConcept C154945302 @default.
- W1590749351 hasConcept C177148314 @default.
- W1590749351 hasConcept C201362023 @default.
- W1590749351 hasConcept C2780598303 @default.
- W1590749351 hasConcept C33923547 @default.
- W1590749351 hasConcept C38365724 @default.
- W1590749351 hasConcept C41008148 @default.
- W1590749351 hasConcept C50644808 @default.
- W1590749351 hasConcept C78458016 @default.
- W1590749351 hasConcept C81388566 @default.
- W1590749351 hasConcept C86803240 @default.
- W1590749351 hasConceptScore W1590749351C105795698 @default.
- W1590749351 hasConceptScore W1590749351C11413529 @default.
- W1590749351 hasConceptScore W1590749351C126255220 @default.
- W1590749351 hasConceptScore W1590749351C134306372 @default.
- W1590749351 hasConceptScore W1590749351C14036430 @default.
- W1590749351 hasConceptScore W1590749351C154945302 @default.
- W1590749351 hasConceptScore W1590749351C177148314 @default.
- W1590749351 hasConceptScore W1590749351C201362023 @default.
- W1590749351 hasConceptScore W1590749351C2780598303 @default.
- W1590749351 hasConceptScore W1590749351C33923547 @default.
- W1590749351 hasConceptScore W1590749351C38365724 @default.
- W1590749351 hasConceptScore W1590749351C41008148 @default.
- W1590749351 hasConceptScore W1590749351C50644808 @default.
- W1590749351 hasConceptScore W1590749351C78458016 @default.
- W1590749351 hasConceptScore W1590749351C81388566 @default.
- W1590749351 hasConceptScore W1590749351C86803240 @default.
- W1590749351 hasLocation W15907493511 @default.
- W1590749351 hasOpenAccess W1590749351 @default.
- W1590749351 hasPrimaryLocation W15907493511 @default.
- W1590749351 hasRelatedWork W134837769 @default.
- W1590749351 hasRelatedWork W1502970866 @default.
- W1590749351 hasRelatedWork W1583347319 @default.
- W1590749351 hasRelatedWork W1584511497 @default.
- W1590749351 hasRelatedWork W1980290744 @default.
- W1590749351 hasRelatedWork W2007295947 @default.
- W1590749351 hasRelatedWork W2023795513 @default.
- W1590749351 hasRelatedWork W2043382734 @default.
- W1590749351 hasRelatedWork W2064534757 @default.
- W1590749351 hasRelatedWork W2083629661 @default.
- W1590749351 hasRelatedWork W2089527616 @default.
- W1590749351 hasRelatedWork W2096868299 @default.
- W1590749351 hasRelatedWork W2113062149 @default.
- W1590749351 hasRelatedWork W2139055047 @default.
- W1590749351 hasRelatedWork W2151796264 @default.
- W1590749351 hasRelatedWork W2154718502 @default.
- W1590749351 hasRelatedWork W2171739084 @default.
- W1590749351 hasRelatedWork W2355617602 @default.
- W1590749351 hasRelatedWork W2385264872 @default.
- W1590749351 hasRelatedWork W2565361090 @default.
- W1590749351 isParatext "false" @default.
- W1590749351 isRetracted "false" @default.
- W1590749351 magId "1590749351" @default.
- W1590749351 workType "book-chapter" @default.