Matches in SemOpenAlex for { <https://semopenalex.org/work/W2087080227> ?p ?o ?g. }
- W2087080227 abstract "Artificial neural networks have the abilities to learn by example and are capable of solving problems that are hard to solve using ordinary rule-based programming. They have many design parameters that affect their performance such as the number and sizes of the hidden layers. Large sizes are slow and small sizes are generally not accurate. Tuning the neural network size is a hard task because the design space is often large and training is often a long process. We use design of experiments techniques to tune the recurrent neural network used in an Arabic handwriting recognition system. We show that best results are achieved with three hidden layers and two subsampling layers. To tune the sizes of these five layers, we use fractional factorial experiment design to limit the number of experiments to a feasible number. Moreover, we replicate the experiment configuration multiple times to overcome the randomness in the training process. The accuracy and time measurements are analyzed and modeled. The two models are then used to locate network sizes that are on the Pareto optimal frontier. The approach described in this paper reduces the label error from 26.2% to 19.8%." @default.
- W2087080227 created "2016-06-24" @default.
- W2087080227 creator A5003723820 @default.
- W2087080227 creator A5036769756 @default.
- W2087080227 creator A5089254754 @default.
- W2087080227 date "2013-01-01" @default.
- W2087080227 modified "2023-09-27" @default.
- W2087080227 title "Tuning Recurrent Neural Networks for Recognizing Handwritten Arabic Words" @default.
- W2087080227 cites W1507336107 @default.
- W2087080227 cites W1585803900 @default.
- W2087080227 cites W159719520 @default.
- W2087080227 cites W1870611936 @default.
- W2087080227 cites W1967109380 @default.
- W2087080227 cites W1967652398 @default.
- W2087080227 cites W1982673299 @default.
- W2087080227 cites W2005518822 @default.
- W2087080227 cites W2011628471 @default.
- W2087080227 cites W2011909934 @default.
- W2087080227 cites W2013825190 @default.
- W2087080227 cites W2033927753 @default.
- W2087080227 cites W2037424248 @default.
- W2087080227 cites W2061160188 @default.
- W2087080227 cites W2064675550 @default.
- W2087080227 cites W2077719796 @default.
- W2087080227 cites W2079537749 @default.
- W2087080227 cites W2079735306 @default.
- W2087080227 cites W2108604074 @default.
- W2087080227 cites W2108994502 @default.
- W2087080227 cites W2114766824 @default.
- W2087080227 cites W2124290836 @default.
- W2087080227 cites W2127141656 @default.
- W2087080227 cites W2134514463 @default.
- W2087080227 cites W2135743131 @default.
- W2087080227 cites W2141756128 @default.
- W2087080227 cites W2144499799 @default.
- W2087080227 cites W2156150815 @default.
- W2087080227 cites W2168504305 @default.
- W2087080227 cites W2169990839 @default.
- W2087080227 cites W2171108470 @default.
- W2087080227 cites W2171963778 @default.
- W2087080227 cites W2181527598 @default.
- W2087080227 cites W2520933715 @default.
- W2087080227 cites W2913525454 @default.
- W2087080227 cites W2917150894 @default.
- W2087080227 cites W53662373 @default.
- W2087080227 cites W3023071679 @default.
- W2087080227 doi "https://doi.org/10.4236/jsea.2013.610064" @default.
- W2087080227 hasPublicationYear "2013" @default.
- W2087080227 type Work @default.
- W2087080227 sameAs 2087080227 @default.
- W2087080227 citedByCount "3" @default.
- W2087080227 countsByYear W20870802272014 @default.
- W2087080227 countsByYear W20870802272016 @default.
- W2087080227 countsByYear W20870802272019 @default.
- W2087080227 crossrefType "journal-article" @default.
- W2087080227 hasAuthorship W2087080227A5003723820 @default.
- W2087080227 hasAuthorship W2087080227A5036769756 @default.
- W2087080227 hasAuthorship W2087080227A5089254754 @default.
- W2087080227 hasBestOaLocation W20870802271 @default.
- W2087080227 hasConcept C105795698 @default.
- W2087080227 hasConcept C110332635 @default.
- W2087080227 hasConcept C111919701 @default.
- W2087080227 hasConcept C119857082 @default.
- W2087080227 hasConcept C125112378 @default.
- W2087080227 hasConcept C13280743 @default.
- W2087080227 hasConcept C134306372 @default.
- W2087080227 hasConcept C151201525 @default.
- W2087080227 hasConcept C153180895 @default.
- W2087080227 hasConcept C154945302 @default.
- W2087080227 hasConcept C185798385 @default.
- W2087080227 hasConcept C205649164 @default.
- W2087080227 hasConcept C2779386606 @default.
- W2087080227 hasConcept C33923547 @default.
- W2087080227 hasConcept C34559072 @default.
- W2087080227 hasConcept C41008148 @default.
- W2087080227 hasConcept C50644808 @default.
- W2087080227 hasConcept C98045186 @default.
- W2087080227 hasConceptScore W2087080227C105795698 @default.
- W2087080227 hasConceptScore W2087080227C110332635 @default.
- W2087080227 hasConceptScore W2087080227C111919701 @default.
- W2087080227 hasConceptScore W2087080227C119857082 @default.
- W2087080227 hasConceptScore W2087080227C125112378 @default.
- W2087080227 hasConceptScore W2087080227C13280743 @default.
- W2087080227 hasConceptScore W2087080227C134306372 @default.
- W2087080227 hasConceptScore W2087080227C151201525 @default.
- W2087080227 hasConceptScore W2087080227C153180895 @default.
- W2087080227 hasConceptScore W2087080227C154945302 @default.
- W2087080227 hasConceptScore W2087080227C185798385 @default.
- W2087080227 hasConceptScore W2087080227C205649164 @default.
- W2087080227 hasConceptScore W2087080227C2779386606 @default.
- W2087080227 hasConceptScore W2087080227C33923547 @default.
- W2087080227 hasConceptScore W2087080227C34559072 @default.
- W2087080227 hasConceptScore W2087080227C41008148 @default.
- W2087080227 hasConceptScore W2087080227C50644808 @default.
- W2087080227 hasConceptScore W2087080227C98045186 @default.
- W2087080227 hasLocation W20870802271 @default.
- W2087080227 hasLocation W20870802272 @default.
- W2087080227 hasOpenAccess W2087080227 @default.
- W2087080227 hasPrimaryLocation W20870802271 @default.
- W2087080227 hasRelatedWork W1566119169 @default.