Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895858327> ?p ?o ?g. }
- W2895858327 endingPage "14" @default.
- W2895858327 startingPage "1" @default.
- W2895858327 abstract "Randomized algorithms have been successfully applied in modeling dynamic system. How do random weights affect system identification and why do they sometimes work well? In this paper, we use the convolutional neural network (CNN) as an identification model to answer these questions. Since the convolution operation is an important property of the dynamic system and in the frequency domain it becomes the product, the CNN model is analyzed in the frequency domain. We first modify the CNN model, so that it can model both the input and the output series. Then we analyze the impact of the random weights of CNN in the frequency domain. We prove the existence of optimal weights and analyze the modeling accuracy under optimal weights and random weights. Through theoretical analysis, we propose a two-step training method and compare it with the random weight algorithm. The proposed CNN model with random weights is validated with three benchmark problems." @default.
- W2895858327 created "2018-10-26" @default.
- W2895858327 creator A5008201587 @default.
- W2895858327 creator A5066451304 @default.
- W2895858327 date "2019-03-01" @default.
- W2895858327 modified "2023-10-05" @default.
- W2895858327 title "Impact of random weights on nonlinear system identification using convolutional neural networks" @default.
- W2895858327 cites W1661947036 @default.
- W2895858327 cites W1844759285 @default.
- W2895858327 cites W1986278072 @default.
- W2895858327 cites W2064675550 @default.
- W2895858327 cites W2109255472 @default.
- W2895858327 cites W2112796928 @default.
- W2895858327 cites W2136922672 @default.
- W2895858327 cites W2138061685 @default.
- W2895858327 cites W2138484437 @default.
- W2895858327 cites W2147800946 @default.
- W2895858327 cites W2159265133 @default.
- W2895858327 cites W2159579247 @default.
- W2895858327 cites W2168893862 @default.
- W2895858327 cites W2586160710 @default.
- W2895858327 cites W2593382986 @default.
- W2895858327 cites W2594014149 @default.
- W2895858327 cites W2809909937 @default.
- W2895858327 cites W4206196235 @default.
- W2895858327 cites W4361807720 @default.
- W2895858327 doi "https://doi.org/10.1016/j.ins.2018.10.019" @default.
- W2895858327 hasPublicationYear "2019" @default.
- W2895858327 type Work @default.
- W2895858327 sameAs 2895858327 @default.
- W2895858327 citedByCount "13" @default.
- W2895858327 countsByYear W28958583272019 @default.
- W2895858327 countsByYear W28958583272020 @default.
- W2895858327 countsByYear W28958583272021 @default.
- W2895858327 countsByYear W28958583272022 @default.
- W2895858327 countsByYear W28958583272023 @default.
- W2895858327 crossrefType "journal-article" @default.
- W2895858327 hasAuthorship W2895858327A5008201587 @default.
- W2895858327 hasAuthorship W2895858327A5066451304 @default.
- W2895858327 hasConcept C11413529 @default.
- W2895858327 hasConcept C116834253 @default.
- W2895858327 hasConcept C119247159 @default.
- W2895858327 hasConcept C121332964 @default.
- W2895858327 hasConcept C13280743 @default.
- W2895858327 hasConcept C134306372 @default.
- W2895858327 hasConcept C143724316 @default.
- W2895858327 hasConcept C151730666 @default.
- W2895858327 hasConcept C153180895 @default.
- W2895858327 hasConcept C154945302 @default.
- W2895858327 hasConcept C158622935 @default.
- W2895858327 hasConcept C185798385 @default.
- W2895858327 hasConcept C19118579 @default.
- W2895858327 hasConcept C205649164 @default.
- W2895858327 hasConcept C31972630 @default.
- W2895858327 hasConcept C33923547 @default.
- W2895858327 hasConcept C36503486 @default.
- W2895858327 hasConcept C41008148 @default.
- W2895858327 hasConcept C45347329 @default.
- W2895858327 hasConcept C50644808 @default.
- W2895858327 hasConcept C59822182 @default.
- W2895858327 hasConcept C62520636 @default.
- W2895858327 hasConcept C67186912 @default.
- W2895858327 hasConcept C77088390 @default.
- W2895858327 hasConcept C81363708 @default.
- W2895858327 hasConcept C86803240 @default.
- W2895858327 hasConceptScore W2895858327C11413529 @default.
- W2895858327 hasConceptScore W2895858327C116834253 @default.
- W2895858327 hasConceptScore W2895858327C119247159 @default.
- W2895858327 hasConceptScore W2895858327C121332964 @default.
- W2895858327 hasConceptScore W2895858327C13280743 @default.
- W2895858327 hasConceptScore W2895858327C134306372 @default.
- W2895858327 hasConceptScore W2895858327C143724316 @default.
- W2895858327 hasConceptScore W2895858327C151730666 @default.
- W2895858327 hasConceptScore W2895858327C153180895 @default.
- W2895858327 hasConceptScore W2895858327C154945302 @default.
- W2895858327 hasConceptScore W2895858327C158622935 @default.
- W2895858327 hasConceptScore W2895858327C185798385 @default.
- W2895858327 hasConceptScore W2895858327C19118579 @default.
- W2895858327 hasConceptScore W2895858327C205649164 @default.
- W2895858327 hasConceptScore W2895858327C31972630 @default.
- W2895858327 hasConceptScore W2895858327C33923547 @default.
- W2895858327 hasConceptScore W2895858327C36503486 @default.
- W2895858327 hasConceptScore W2895858327C41008148 @default.
- W2895858327 hasConceptScore W2895858327C45347329 @default.
- W2895858327 hasConceptScore W2895858327C50644808 @default.
- W2895858327 hasConceptScore W2895858327C59822182 @default.
- W2895858327 hasConceptScore W2895858327C62520636 @default.
- W2895858327 hasConceptScore W2895858327C67186912 @default.
- W2895858327 hasConceptScore W2895858327C77088390 @default.
- W2895858327 hasConceptScore W2895858327C81363708 @default.
- W2895858327 hasConceptScore W2895858327C86803240 @default.
- W2895858327 hasLocation W28958583271 @default.
- W2895858327 hasOpenAccess W2895858327 @default.
- W2895858327 hasPrimaryLocation W28958583271 @default.
- W2895858327 hasRelatedWork W1912925187 @default.
- W2895858327 hasRelatedWork W2024239133 @default.
- W2895858327 hasRelatedWork W2755240195 @default.
- W2895858327 hasRelatedWork W2766634277 @default.