Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963359648> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2963359648 abstract "Deep Learning methods have proven to be very successful in classifying large data sets of high feature dimensionality. However, their success usually implies very long training times. In this paper we examine learning methods combining the Random Neural Network, a biologically inspired neural network and the Extreme Learning Machine that achieve state of the art classification performance while requiring much shorter training time. The Random Neural Network is a integrate and fire computational model of a neural network whose mathematical structure permits the efficient analysis of large ensembles of neurons. An activation function is derived from the RNN and used in an Extreme Learning Machine. We compare the performance of this combination against the ELM with various activation functions, we reduce the input dimensionality via PCA and compare its performance vs. autoencoder based versions of the RNN-ELM." @default.
- W2963359648 created "2019-07-30" @default.
- W2963359648 creator A5020902651 @default.
- W2963359648 date "2017-05-01" @default.
- W2963359648 modified "2023-09-25" @default.
- W2963359648 title "The RNN-ELM classifier" @default.
- W2963359648 cites W2006908712 @default.
- W2963359648 cites W2009786043 @default.
- W2963359648 cites W2010470943 @default.
- W2963359648 cites W2028319341 @default.
- W2963359648 cites W2037757210 @default.
- W2963359648 cites W2044871439 @default.
- W2963359648 cites W2045643717 @default.
- W2963359648 cites W2056494836 @default.
- W2963359648 cites W2079725295 @default.
- W2963359648 cites W2095613246 @default.
- W2963359648 cites W2100556411 @default.
- W2963359648 cites W2106280476 @default.
- W2963359648 cites W2108069432 @default.
- W2963359648 cites W2111072639 @default.
- W2963359648 cites W2112796928 @default.
- W2963359648 cites W2122376145 @default.
- W2963359648 cites W2134557905 @default.
- W2963359648 cites W2135046866 @default.
- W2963359648 cites W2147374078 @default.
- W2963359648 cites W2148461049 @default.
- W2963359648 cites W2149570311 @default.
- W2963359648 cites W2160820123 @default.
- W2963359648 cites W2163605009 @default.
- W2963359648 cites W2552324112 @default.
- W2963359648 cites W2994602700 @default.
- W2963359648 doi "https://doi.org/10.1109/ijcnn.2017.7966188" @default.
- W2963359648 hasPublicationYear "2017" @default.
- W2963359648 type Work @default.
- W2963359648 sameAs 2963359648 @default.
- W2963359648 citedByCount "0" @default.
- W2963359648 crossrefType "proceedings-article" @default.
- W2963359648 hasAuthorship W2963359648A5020902651 @default.
- W2963359648 hasConcept C101738243 @default.
- W2963359648 hasConcept C108583219 @default.
- W2963359648 hasConcept C111030470 @default.
- W2963359648 hasConcept C119857082 @default.
- W2963359648 hasConcept C147168706 @default.
- W2963359648 hasConcept C153180895 @default.
- W2963359648 hasConcept C154945302 @default.
- W2963359648 hasConcept C2780150128 @default.
- W2963359648 hasConcept C38365724 @default.
- W2963359648 hasConcept C41008148 @default.
- W2963359648 hasConcept C50644808 @default.
- W2963359648 hasConcept C70518039 @default.
- W2963359648 hasConcept C95623464 @default.
- W2963359648 hasConceptScore W2963359648C101738243 @default.
- W2963359648 hasConceptScore W2963359648C108583219 @default.
- W2963359648 hasConceptScore W2963359648C111030470 @default.
- W2963359648 hasConceptScore W2963359648C119857082 @default.
- W2963359648 hasConceptScore W2963359648C147168706 @default.
- W2963359648 hasConceptScore W2963359648C153180895 @default.
- W2963359648 hasConceptScore W2963359648C154945302 @default.
- W2963359648 hasConceptScore W2963359648C2780150128 @default.
- W2963359648 hasConceptScore W2963359648C38365724 @default.
- W2963359648 hasConceptScore W2963359648C41008148 @default.
- W2963359648 hasConceptScore W2963359648C50644808 @default.
- W2963359648 hasConceptScore W2963359648C70518039 @default.
- W2963359648 hasConceptScore W2963359648C95623464 @default.
- W2963359648 hasLocation W29633596481 @default.
- W2963359648 hasOpenAccess W2963359648 @default.
- W2963359648 hasPrimaryLocation W29633596481 @default.
- W2963359648 hasRelatedWork W1819700463 @default.
- W2963359648 hasRelatedWork W1989999734 @default.
- W2963359648 hasRelatedWork W2008817470 @default.
- W2963359648 hasRelatedWork W2016355702 @default.
- W2963359648 hasRelatedWork W2031878488 @default.
- W2963359648 hasRelatedWork W2049797988 @default.
- W2963359648 hasRelatedWork W2073996697 @default.
- W2963359648 hasRelatedWork W2075157159 @default.
- W2963359648 hasRelatedWork W2079774538 @default.
- W2963359648 hasRelatedWork W2097442613 @default.
- W2963359648 hasRelatedWork W2214837383 @default.
- W2963359648 hasRelatedWork W2249599938 @default.
- W2963359648 hasRelatedWork W2249917527 @default.
- W2963359648 hasRelatedWork W2488320208 @default.
- W2963359648 hasRelatedWork W2510647175 @default.
- W2963359648 hasRelatedWork W2525538987 @default.
- W2963359648 hasRelatedWork W2586185552 @default.
- W2963359648 hasRelatedWork W3091039798 @default.
- W2963359648 hasRelatedWork W3180991119 @default.
- W2963359648 hasRelatedWork W612398116 @default.
- W2963359648 isParatext "false" @default.
- W2963359648 isRetracted "false" @default.
- W2963359648 magId "2963359648" @default.
- W2963359648 workType "article" @default.