Matches in SemOpenAlex for { <https://semopenalex.org/work/W2022141188> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2022141188 endingPage "311" @default.
- W2022141188 startingPage "295" @default.
- W2022141188 abstract "Mapping properties of multi-layer, feedforward artificial neural networks are analyzed using modified backpropagation training with forgetting (decay) of the connection weights. Neural nets trained by forgetting algorithm are not sensitive to the initial choice of the network, and the trained network structure can be used for knowledge acquisition regarding the feature classes. The accuracy of the non-linear mapping realized by layered neural networks is limited in the sense of minimum classification error and it can be estimated based on the a posteriori probability densities of the training classes. It is shown in this paper that backpropagation with forgetting is a convenient tool to implement finite accuracy of learning.The proposed strategy has been used for anomaly detection in actual time series. It is shown that neural networks trained by forgetting algorithm have better generalization capabilities than those trained by standard backpropagation. The analyzed feature classes have been characterized by making use of the information extracted from the structure of the trained network." @default.
- W2022141188 created "2016-06-24" @default.
- W2022141188 creator A5003742432 @default.
- W2022141188 creator A5007501932 @default.
- W2022141188 creator A5051218868 @default.
- W2022141188 creator A5051910428 @default.
- W2022141188 date "1996-10-01" @default.
- W2022141188 modified "2023-09-27" @default.
- W2022141188 title "On the accuracy of mapping by neural networks trained by backpropagation with forgetting" @default.
- W2022141188 cites W151940559 @default.
- W2022141188 cites W1964168965 @default.
- W2022141188 cites W1982921451 @default.
- W2022141188 cites W2004649581 @default.
- W2022141188 cites W2010656743 @default.
- W2022141188 cites W2097533491 @default.
- W2022141188 cites W2097666287 @default.
- W2022141188 cites W2131111770 @default.
- W2022141188 cites W2131573251 @default.
- W2022141188 cites W2141278204 @default.
- W2022141188 cites W2145085734 @default.
- W2022141188 cites W2164001754 @default.
- W2022141188 doi "https://doi.org/10.1016/0925-2312(95)00094-1" @default.
- W2022141188 hasPublicationYear "1996" @default.
- W2022141188 type Work @default.
- W2022141188 sameAs 2022141188 @default.
- W2022141188 citedByCount "27" @default.
- W2022141188 countsByYear W20221411882012 @default.
- W2022141188 countsByYear W20221411882013 @default.
- W2022141188 countsByYear W20221411882014 @default.
- W2022141188 countsByYear W20221411882017 @default.
- W2022141188 countsByYear W20221411882019 @default.
- W2022141188 countsByYear W20221411882022 @default.
- W2022141188 crossrefType "journal-article" @default.
- W2022141188 hasAuthorship W2022141188A5003742432 @default.
- W2022141188 hasAuthorship W2022141188A5007501932 @default.
- W2022141188 hasAuthorship W2022141188A5051218868 @default.
- W2022141188 hasAuthorship W2022141188A5051910428 @default.
- W2022141188 hasConcept C119857082 @default.
- W2022141188 hasConcept C153180895 @default.
- W2022141188 hasConcept C154945302 @default.
- W2022141188 hasConcept C155032097 @default.
- W2022141188 hasConcept C15744967 @default.
- W2022141188 hasConcept C180747234 @default.
- W2022141188 hasConcept C41008148 @default.
- W2022141188 hasConcept C50644808 @default.
- W2022141188 hasConcept C7149132 @default.
- W2022141188 hasConceptScore W2022141188C119857082 @default.
- W2022141188 hasConceptScore W2022141188C153180895 @default.
- W2022141188 hasConceptScore W2022141188C154945302 @default.
- W2022141188 hasConceptScore W2022141188C155032097 @default.
- W2022141188 hasConceptScore W2022141188C15744967 @default.
- W2022141188 hasConceptScore W2022141188C180747234 @default.
- W2022141188 hasConceptScore W2022141188C41008148 @default.
- W2022141188 hasConceptScore W2022141188C50644808 @default.
- W2022141188 hasConceptScore W2022141188C7149132 @default.
- W2022141188 hasIssue "2-4" @default.
- W2022141188 hasLocation W20221411881 @default.
- W2022141188 hasOpenAccess W2022141188 @default.
- W2022141188 hasPrimaryLocation W20221411881 @default.
- W2022141188 hasRelatedWork W2048308819 @default.
- W2022141188 hasRelatedWork W2075600602 @default.
- W2022141188 hasRelatedWork W2096356999 @default.
- W2022141188 hasRelatedWork W2379874775 @default.
- W2022141188 hasRelatedWork W2381360513 @default.
- W2022141188 hasRelatedWork W3201709409 @default.
- W2022141188 hasRelatedWork W777115257 @default.
- W2022141188 hasRelatedWork W1629725936 @default.
- W2022141188 hasRelatedWork W2179998186 @default.
- W2022141188 hasRelatedWork W2187285467 @default.
- W2022141188 hasVolume "13" @default.
- W2022141188 isParatext "false" @default.
- W2022141188 isRetracted "false" @default.
- W2022141188 magId "2022141188" @default.
- W2022141188 workType "article" @default.