Matches in SemOpenAlex for { <https://semopenalex.org/work/W2101995797> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2101995797 abstract "Multilayer feedforward network trained by backpropagation algorithm suffers from slow learning speed. One of the reasons of slow convergence is the diminishing value of the derivative of the commonly used activation functions as the nodes approaches saturated values. In this paper, we present a new activation function to accelerate backpropagation learning. A comparison among the commonly used activation functions, recently proposed logarithmic function and the proposed activation function shows accelerated convergence with the proposed one. This activation function can be used in conjunction with other techniques to further accelerate the learning speed or reduce the chance of being trapped in local minima. Simulation using this activation function shows improvement in the learning speed compared with other commonly used functions and the new activation function proposed by Bilski (2000). This function may also be used in other multilayer feedforward training algorithms." @default.
- W2101995797 created "2016-06-24" @default.
- W2101995797 creator A5013199739 @default.
- W2101995797 creator A5034717122 @default.
- W2101995797 date "2003-06-25" @default.
- W2101995797 modified "2023-10-05" @default.
- W2101995797 title "A note on activation function in multilayer feedforward learning" @default.
- W2101995797 cites W1541269238 @default.
- W2101995797 cites W2010128305 @default.
- W2101995797 cites W2022540064 @default.
- W2101995797 cites W2087836750 @default.
- W2101995797 cites W2104030629 @default.
- W2101995797 cites W2143908786 @default.
- W2101995797 cites W2160208155 @default.
- W2101995797 cites W4300402905 @default.
- W2101995797 doi "https://doi.org/10.1109/ijcnn.2002.1005526" @default.
- W2101995797 hasPublicationYear "2003" @default.
- W2101995797 type Work @default.
- W2101995797 sameAs 2101995797 @default.
- W2101995797 citedByCount "26" @default.
- W2101995797 countsByYear W21019957972012 @default.
- W2101995797 countsByYear W21019957972013 @default.
- W2101995797 countsByYear W21019957972014 @default.
- W2101995797 countsByYear W21019957972015 @default.
- W2101995797 countsByYear W21019957972016 @default.
- W2101995797 countsByYear W21019957972017 @default.
- W2101995797 countsByYear W21019957972018 @default.
- W2101995797 countsByYear W21019957972019 @default.
- W2101995797 countsByYear W21019957972021 @default.
- W2101995797 countsByYear W21019957972022 @default.
- W2101995797 crossrefType "proceedings-article" @default.
- W2101995797 hasAuthorship W2101995797A5013199739 @default.
- W2101995797 hasAuthorship W2101995797A5034717122 @default.
- W2101995797 hasConcept C11413529 @default.
- W2101995797 hasConcept C127413603 @default.
- W2101995797 hasConcept C133731056 @default.
- W2101995797 hasConcept C134306372 @default.
- W2101995797 hasConcept C14036430 @default.
- W2101995797 hasConcept C154945302 @default.
- W2101995797 hasConcept C155032097 @default.
- W2101995797 hasConcept C162324750 @default.
- W2101995797 hasConcept C186633575 @default.
- W2101995797 hasConcept C2777303404 @default.
- W2101995797 hasConcept C33923547 @default.
- W2101995797 hasConcept C38365724 @default.
- W2101995797 hasConcept C38858127 @default.
- W2101995797 hasConcept C41008148 @default.
- W2101995797 hasConcept C50522688 @default.
- W2101995797 hasConcept C50644808 @default.
- W2101995797 hasConcept C78458016 @default.
- W2101995797 hasConcept C86803240 @default.
- W2101995797 hasConceptScore W2101995797C11413529 @default.
- W2101995797 hasConceptScore W2101995797C127413603 @default.
- W2101995797 hasConceptScore W2101995797C133731056 @default.
- W2101995797 hasConceptScore W2101995797C134306372 @default.
- W2101995797 hasConceptScore W2101995797C14036430 @default.
- W2101995797 hasConceptScore W2101995797C154945302 @default.
- W2101995797 hasConceptScore W2101995797C155032097 @default.
- W2101995797 hasConceptScore W2101995797C162324750 @default.
- W2101995797 hasConceptScore W2101995797C186633575 @default.
- W2101995797 hasConceptScore W2101995797C2777303404 @default.
- W2101995797 hasConceptScore W2101995797C33923547 @default.
- W2101995797 hasConceptScore W2101995797C38365724 @default.
- W2101995797 hasConceptScore W2101995797C38858127 @default.
- W2101995797 hasConceptScore W2101995797C41008148 @default.
- W2101995797 hasConceptScore W2101995797C50522688 @default.
- W2101995797 hasConceptScore W2101995797C50644808 @default.
- W2101995797 hasConceptScore W2101995797C78458016 @default.
- W2101995797 hasConceptScore W2101995797C86803240 @default.
- W2101995797 hasLocation W21019957971 @default.
- W2101995797 hasOpenAccess W2101995797 @default.
- W2101995797 hasPrimaryLocation W21019957971 @default.
- W2101995797 hasRelatedWork W1552938653 @default.
- W2101995797 hasRelatedWork W1567571245 @default.
- W2101995797 hasRelatedWork W1604847762 @default.
- W2101995797 hasRelatedWork W1867443617 @default.
- W2101995797 hasRelatedWork W2082482750 @default.
- W2101995797 hasRelatedWork W2244330272 @default.
- W2101995797 hasRelatedWork W2258992572 @default.
- W2101995797 hasRelatedWork W2349436282 @default.
- W2101995797 hasRelatedWork W2391384657 @default.
- W2101995797 hasRelatedWork W2402931317 @default.
- W2101995797 isParatext "false" @default.
- W2101995797 isRetracted "false" @default.
- W2101995797 magId "2101995797" @default.
- W2101995797 workType "article" @default.