Matches in SemOpenAlex for { <https://semopenalex.org/work/W2018889731> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2018889731 abstract "The neural network community has recently shown a considerably interest in combining multiple neural networks (NNs). Such a combination usually improves the performance over a single NN because different NNs can complement each other. To achieve improved performance, the individual NNs must be trained independently. In this paper, three NNs are trained using the Ranking Figure of Merit objective function (with different parameters) that we introduced last year. We introduce a new method of combining NNs, which we call pooled objective function. The objective function is calculated for each NN and averaged to arrive at the pooled objective function. The combined vote is the class with the best pooled objective function. It is shown that the frequently used scheme of averaging the outputs is equivalent to the pooled mean squared error." @default.
- W2018889731 created "2016-06-24" @default.
- W2018889731 creator A5055345322 @default.
- W2018889731 creator A5072991163 @default.
- W2018889731 date "1996-03-22" @default.
- W2018889731 modified "2023-09-26" @default.
- W2018889731 title "<title>Combining neural networks using the ranking figure of merit</title>" @default.
- W2018889731 doi "https://doi.org/10.1117/12.235912" @default.
- W2018889731 hasPublicationYear "1996" @default.
- W2018889731 type Work @default.
- W2018889731 sameAs 2018889731 @default.
- W2018889731 citedByCount "1" @default.
- W2018889731 crossrefType "proceedings-article" @default.
- W2018889731 hasAuthorship W2018889731A5055345322 @default.
- W2018889731 hasAuthorship W2018889731A5072991163 @default.
- W2018889731 hasConcept C104317684 @default.
- W2018889731 hasConcept C105795698 @default.
- W2018889731 hasConcept C112313634 @default.
- W2018889731 hasConcept C11413529 @default.
- W2018889731 hasConcept C119857082 @default.
- W2018889731 hasConcept C127716648 @default.
- W2018889731 hasConcept C130277099 @default.
- W2018889731 hasConcept C139945424 @default.
- W2018889731 hasConcept C14036430 @default.
- W2018889731 hasConcept C153180895 @default.
- W2018889731 hasConcept C154945302 @default.
- W2018889731 hasConcept C185592680 @default.
- W2018889731 hasConcept C188082640 @default.
- W2018889731 hasConcept C189430467 @default.
- W2018889731 hasConcept C31972630 @default.
- W2018889731 hasConcept C33923547 @default.
- W2018889731 hasConcept C41008148 @default.
- W2018889731 hasConcept C50644808 @default.
- W2018889731 hasConcept C55493867 @default.
- W2018889731 hasConcept C78458016 @default.
- W2018889731 hasConcept C86803240 @default.
- W2018889731 hasConceptScore W2018889731C104317684 @default.
- W2018889731 hasConceptScore W2018889731C105795698 @default.
- W2018889731 hasConceptScore W2018889731C112313634 @default.
- W2018889731 hasConceptScore W2018889731C11413529 @default.
- W2018889731 hasConceptScore W2018889731C119857082 @default.
- W2018889731 hasConceptScore W2018889731C127716648 @default.
- W2018889731 hasConceptScore W2018889731C130277099 @default.
- W2018889731 hasConceptScore W2018889731C139945424 @default.
- W2018889731 hasConceptScore W2018889731C14036430 @default.
- W2018889731 hasConceptScore W2018889731C153180895 @default.
- W2018889731 hasConceptScore W2018889731C154945302 @default.
- W2018889731 hasConceptScore W2018889731C185592680 @default.
- W2018889731 hasConceptScore W2018889731C188082640 @default.
- W2018889731 hasConceptScore W2018889731C189430467 @default.
- W2018889731 hasConceptScore W2018889731C31972630 @default.
- W2018889731 hasConceptScore W2018889731C33923547 @default.
- W2018889731 hasConceptScore W2018889731C41008148 @default.
- W2018889731 hasConceptScore W2018889731C50644808 @default.
- W2018889731 hasConceptScore W2018889731C55493867 @default.
- W2018889731 hasConceptScore W2018889731C78458016 @default.
- W2018889731 hasConceptScore W2018889731C86803240 @default.
- W2018889731 hasLocation W20188897311 @default.
- W2018889731 hasOpenAccess W2018889731 @default.
- W2018889731 hasPrimaryLocation W20188897311 @default.
- W2018889731 hasRelatedWork W1493706908 @default.
- W2018889731 hasRelatedWork W1529984711 @default.
- W2018889731 hasRelatedWork W1576177170 @default.
- W2018889731 hasRelatedWork W1600128224 @default.
- W2018889731 hasRelatedWork W1683707134 @default.
- W2018889731 hasRelatedWork W1988368462 @default.
- W2018889731 hasRelatedWork W1992274498 @default.
- W2018889731 hasRelatedWork W2085381944 @default.
- W2018889731 hasRelatedWork W2088648328 @default.
- W2018889731 hasRelatedWork W2165240295 @default.
- W2018889731 hasRelatedWork W2237209205 @default.
- W2018889731 hasRelatedWork W2375446027 @default.
- W2018889731 hasRelatedWork W2377773984 @default.
- W2018889731 hasRelatedWork W2411387771 @default.
- W2018889731 hasRelatedWork W2786234252 @default.
- W2018889731 hasRelatedWork W2892198395 @default.
- W2018889731 hasRelatedWork W2993212056 @default.
- W2018889731 hasRelatedWork W3080448949 @default.
- W2018889731 hasRelatedWork W54626961 @default.
- W2018889731 hasRelatedWork W138720755 @default.
- W2018889731 isParatext "false" @default.
- W2018889731 isRetracted "false" @default.
- W2018889731 magId "2018889731" @default.
- W2018889731 workType "article" @default.