Matches in SemOpenAlex for { <https://semopenalex.org/work/W2554232006> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2554232006 abstract "This paper describes two new algorithms for optimising the structure of trained Evolving Connectionist System (ECoS) artificial neural networks (ANN). It also presents the results of preliminary empirical evaluations of the algorithms. While ECoS are fast and efficient constructive ANN algorithms they can lose efficiency if they are allowed to grow too large. The algorithms presented in this paper reduce the size of a trained ECoS while retaining the knowledge that the ECoS has learned. That is, they remove redundant elements of the ECoS structure in such a way that the performance of the network is not reduced. The experimental evaluations showed that each algorithm is capable of achieving this to a different degree over different data sets. Optimisation of the parameters of one of the algorithms using an evolutionary algorithm yielded better results. While the work reported in this paper is preliminary, the results are promising and the algorithms have the potential to enhance the usefulness of ECoS ANN." @default.
- W2554232006 created "2016-11-30" @default.
- W2554232006 creator A5066388349 @default.
- W2554232006 date "2016-07-01" @default.
- W2554232006 modified "2023-09-26" @default.
- W2554232006 title "Sleep learning and Max-Min aggregation of Evolving Connectionist Systems" @default.
- W2554232006 cites W1504078279 @default.
- W2554232006 cites W1520580877 @default.
- W2554232006 cites W160399367 @default.
- W2554232006 cites W1987581229 @default.
- W2554232006 cites W2002016471 @default.
- W2554232006 cites W2007541629 @default.
- W2554232006 cites W2010429723 @default.
- W2554232006 cites W2081390277 @default.
- W2554232006 cites W2134105639 @default.
- W2554232006 cites W2147368400 @default.
- W2554232006 cites W2150197630 @default.
- W2554232006 cites W2165307965 @default.
- W2554232006 cites W2171855248 @default.
- W2554232006 cites W2304531936 @default.
- W2554232006 cites W3120740533 @default.
- W2554232006 cites W70449568 @default.
- W2554232006 doi "https://doi.org/10.1109/ijcnn.2016.7727764" @default.
- W2554232006 hasPublicationYear "2016" @default.
- W2554232006 type Work @default.
- W2554232006 sameAs 2554232006 @default.
- W2554232006 citedByCount "1" @default.
- W2554232006 countsByYear W25542320062017 @default.
- W2554232006 crossrefType "proceedings-article" @default.
- W2554232006 hasAuthorship W2554232006A5066388349 @default.
- W2554232006 hasConcept C111919701 @default.
- W2554232006 hasConcept C119857082 @default.
- W2554232006 hasConcept C154945302 @default.
- W2554232006 hasConcept C2778701210 @default.
- W2554232006 hasConcept C41008148 @default.
- W2554232006 hasConcept C50644808 @default.
- W2554232006 hasConcept C8521452 @default.
- W2554232006 hasConcept C98045186 @default.
- W2554232006 hasConceptScore W2554232006C111919701 @default.
- W2554232006 hasConceptScore W2554232006C119857082 @default.
- W2554232006 hasConceptScore W2554232006C154945302 @default.
- W2554232006 hasConceptScore W2554232006C2778701210 @default.
- W2554232006 hasConceptScore W2554232006C41008148 @default.
- W2554232006 hasConceptScore W2554232006C50644808 @default.
- W2554232006 hasConceptScore W2554232006C8521452 @default.
- W2554232006 hasConceptScore W2554232006C98045186 @default.
- W2554232006 hasLocation W25542320061 @default.
- W2554232006 hasOpenAccess W2554232006 @default.
- W2554232006 hasPrimaryLocation W25542320061 @default.
- W2554232006 hasRelatedWork W132708474 @default.
- W2554232006 hasRelatedWork W1513196210 @default.
- W2554232006 hasRelatedWork W1527772799 @default.
- W2554232006 hasRelatedWork W2069319653 @default.
- W2554232006 hasRelatedWork W2104934474 @default.
- W2554232006 hasRelatedWork W2106057311 @default.
- W2554232006 hasRelatedWork W2121987530 @default.
- W2554232006 hasRelatedWork W2127245615 @default.
- W2554232006 hasRelatedWork W2135743357 @default.
- W2554232006 hasRelatedWork W2144788105 @default.
- W2554232006 hasRelatedWork W2163178248 @default.
- W2554232006 hasRelatedWork W2186782138 @default.
- W2554232006 hasRelatedWork W2549539357 @default.
- W2554232006 hasRelatedWork W2607780746 @default.
- W2554232006 hasRelatedWork W3018159093 @default.
- W2554232006 hasRelatedWork W3086765375 @default.
- W2554232006 hasRelatedWork W3097132272 @default.
- W2554232006 hasRelatedWork W3135363398 @default.
- W2554232006 hasRelatedWork W3146497429 @default.
- W2554232006 hasRelatedWork W586773592 @default.
- W2554232006 isParatext "false" @default.
- W2554232006 isRetracted "false" @default.
- W2554232006 magId "2554232006" @default.
- W2554232006 workType "article" @default.