FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2103172839> ?p ?o ?g. }

• W2103172839 abstract "This paper proposes a task decomposition method, which divides a large-scale learning problem into multiple limited-scale pairs of training subsets and cross validation (CV) subsets. Correspondingly, modular multilayer perceptrons are set up. At first, one training subset only consists of its own class and several most neighboring categories, and then some classes in the CV subset are moved into it according to the generalization error of the module. This work presents an empirical formula for selecting the initial number of hidden nodes, and a method for determining the optimal number of hidden units with the help of singular value decomposition. The result for letter recognition shows that the above methods are quite effective." @default.
• W2103172839 created "2016-06-24" @default.
• W2103172839 creator A5004583405 @default.
• W2103172839 creator A5007052738 @default.
• W2103172839 creator A5089246314 @default.
• W2103172839 creator A5090976367 @default.
• W2103172839 date "2005-02-28" @default.
• W2103172839 modified "2023-09-24" @default.
• W2103172839 title "Adaptive task decomposition and modular multilayer perceptrons for letter recognition" @default.
• W2103172839 cites W1976990135 @default.
• W2103172839 cites W1982610692 @default.
• W2103172839 cites W2004075725 @default.
• W2103172839 cites W2009466980 @default.
• W2103172839 cites W2019806426 @default.
• W2103172839 cites W2020663993 @default.
• W2103172839 cites W2021404082 @default.
• W2103172839 cites W2034613413 @default.
• W2103172839 cites W2034767890 @default.
• W2103172839 cites W2040884411 @default.
• W2103172839 cites W2070229819 @default.
• W2103172839 cites W2099741732 @default.
• W2103172839 cites W2100816322 @default.
• W2103172839 cites W2101349570 @default.
• W2103172839 cites W2113890143 @default.
• W2103172839 cites W2127545084 @default.
• W2103172839 cites W2134631822 @default.
• W2103172839 cites W2143533311 @default.
• W2103172839 cites W2146615496 @default.
• W2103172839 cites W2149298154 @default.
• W2103172839 cites W2153382583 @default.
• W2103172839 cites W2153436198 @default.
• W2103172839 cites W2158449659 @default.
• W2103172839 cites W2160177263 @default.
• W2103172839 cites W2164276496 @default.
• W2103172839 cites W2165367035 @default.
• W2103172839 cites W2172000360 @default.
• W2103172839 cites W69318073 @default.
• W2103172839 doi "https://doi.org/10.1109/ijcnn.2004.1381131" @default.
• W2103172839 hasPublicationYear "2005" @default.
• W2103172839 type Work @default.
• W2103172839 sameAs 2103172839 @default.
• W2103172839 citedByCount "0" @default.
• W2103172839 crossrefType "proceedings-article" @default.
• W2103172839 hasAuthorship W2103172839A5004583405 @default.
• W2103172839 hasAuthorship W2103172839A5007052738 @default.
• W2103172839 hasAuthorship W2103172839A5089246314 @default.
• W2103172839 hasAuthorship W2103172839A5090976367 @default.
• W2103172839 hasConcept C101468663 @default.
• W2103172839 hasConcept C111919701 @default.
• W2103172839 hasConcept C11413529 @default.
• W2103172839 hasConcept C119857082 @default.
• W2103172839 hasConcept C121332964 @default.
• W2103172839 hasConcept C124681953 @default.
• W2103172839 hasConcept C127413603 @default.
• W2103172839 hasConcept C134306372 @default.
• W2103172839 hasConcept C153180895 @default.
• W2103172839 hasConcept C154945302 @default.
• W2103172839 hasConcept C177148314 @default.
• W2103172839 hasConcept C177264268 @default.
• W2103172839 hasConcept C18903297 @default.
• W2103172839 hasConcept C199360897 @default.
• W2103172839 hasConcept C201995342 @default.
• W2103172839 hasConcept C22789450 @default.
• W2103172839 hasConcept C2777212361 @default.
• W2103172839 hasConcept C2778755073 @default.
• W2103172839 hasConcept C2780451532 @default.
• W2103172839 hasConcept C33923547 @default.
• W2103172839 hasConcept C41008148 @default.
• W2103172839 hasConcept C50644808 @default.
• W2103172839 hasConcept C60908668 @default.
• W2103172839 hasConcept C62520636 @default.
• W2103172839 hasConcept C86803240 @default.
• W2103172839 hasConceptScore W2103172839C101468663 @default.
• W2103172839 hasConceptScore W2103172839C111919701 @default.
• W2103172839 hasConceptScore W2103172839C11413529 @default.
• W2103172839 hasConceptScore W2103172839C119857082 @default.
• W2103172839 hasConceptScore W2103172839C121332964 @default.
• W2103172839 hasConceptScore W2103172839C124681953 @default.
• W2103172839 hasConceptScore W2103172839C127413603 @default.
• W2103172839 hasConceptScore W2103172839C134306372 @default.
• W2103172839 hasConceptScore W2103172839C153180895 @default.
• W2103172839 hasConceptScore W2103172839C154945302 @default.
• W2103172839 hasConceptScore W2103172839C177148314 @default.
• W2103172839 hasConceptScore W2103172839C177264268 @default.
• W2103172839 hasConceptScore W2103172839C18903297 @default.
• W2103172839 hasConceptScore W2103172839C199360897 @default.
• W2103172839 hasConceptScore W2103172839C201995342 @default.
• W2103172839 hasConceptScore W2103172839C22789450 @default.
• W2103172839 hasConceptScore W2103172839C2777212361 @default.
• W2103172839 hasConceptScore W2103172839C2778755073 @default.
• W2103172839 hasConceptScore W2103172839C2780451532 @default.
• W2103172839 hasConceptScore W2103172839C33923547 @default.
• W2103172839 hasConceptScore W2103172839C41008148 @default.
• W2103172839 hasConceptScore W2103172839C50644808 @default.
• W2103172839 hasConceptScore W2103172839C60908668 @default.
• W2103172839 hasConceptScore W2103172839C62520636 @default.
• W2103172839 hasConceptScore W2103172839C86803240 @default.
• W2103172839 hasLocation W21031728391 @default.
• W2103172839 hasOpenAccess W2103172839 @default.
• W2103172839 hasPrimaryLocation W21031728391 @default.

• next