Matches in SemOpenAlex for { <https://semopenalex.org/work/W917225955> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W917225955 endingPage "70" @default.
- W917225955 startingPage "66" @default.
- W917225955 abstract "In this paper a new learning algorithm for curvature smoothing and improved generalization for multi-layer neural networks is proposed. To enhance the generalization ability a constraint term of hidden neuron activations is added to the conventional output error, which gives the curvature smoothing characteristics to multi-layer neural networks. When the total cost consisted of the output error and hidden error is minimized by gradient-descent methods, the additional descent term gives not only the Hebbian learning but also the synaptic weight decay. Therefore it incorporates error back-propagation, Hebbian, and weight decay, and additional computational requirements to the standard error back-propagation is negligible. From the computer simulation of the time series prediction with Santafe competition data it is shown that the proposed learning algorithm gives much better generalization performance." @default.
- W917225955 created "2016-06-24" @default.
- W917225955 creator A5016475473 @default.
- W917225955 date "1997-01-01" @default.
- W917225955 modified "2023-09-26" @default.
- W917225955 title "Time Series Prediction Using a Multi-layer Neural Network with Low Pass Filter Characteristics" @default.
- W917225955 hasPublicationYear "1997" @default.
- W917225955 type Work @default.
- W917225955 sameAs 917225955 @default.
- W917225955 citedByCount "0" @default.
- W917225955 crossrefType "journal-article" @default.
- W917225955 hasAuthorship W917225955A5016475473 @default.
- W917225955 hasConcept C106131492 @default.
- W917225955 hasConcept C111437709 @default.
- W917225955 hasConcept C11413529 @default.
- W917225955 hasConcept C134306372 @default.
- W917225955 hasConcept C143724316 @default.
- W917225955 hasConcept C151730666 @default.
- W917225955 hasConcept C153258448 @default.
- W917225955 hasConcept C154945302 @default.
- W917225955 hasConcept C155032097 @default.
- W917225955 hasConcept C177148314 @default.
- W917225955 hasConcept C195065555 @default.
- W917225955 hasConcept C2524010 @default.
- W917225955 hasConcept C31972630 @default.
- W917225955 hasConcept C33923547 @default.
- W917225955 hasConcept C3770464 @default.
- W917225955 hasConcept C41008148 @default.
- W917225955 hasConcept C50644808 @default.
- W917225955 hasConcept C86803240 @default.
- W917225955 hasConceptScore W917225955C106131492 @default.
- W917225955 hasConceptScore W917225955C111437709 @default.
- W917225955 hasConceptScore W917225955C11413529 @default.
- W917225955 hasConceptScore W917225955C134306372 @default.
- W917225955 hasConceptScore W917225955C143724316 @default.
- W917225955 hasConceptScore W917225955C151730666 @default.
- W917225955 hasConceptScore W917225955C153258448 @default.
- W917225955 hasConceptScore W917225955C154945302 @default.
- W917225955 hasConceptScore W917225955C155032097 @default.
- W917225955 hasConceptScore W917225955C177148314 @default.
- W917225955 hasConceptScore W917225955C195065555 @default.
- W917225955 hasConceptScore W917225955C2524010 @default.
- W917225955 hasConceptScore W917225955C31972630 @default.
- W917225955 hasConceptScore W917225955C33923547 @default.
- W917225955 hasConceptScore W917225955C3770464 @default.
- W917225955 hasConceptScore W917225955C41008148 @default.
- W917225955 hasConceptScore W917225955C50644808 @default.
- W917225955 hasConceptScore W917225955C86803240 @default.
- W917225955 hasIssue "1" @default.
- W917225955 hasLocation W9172259551 @default.
- W917225955 hasOpenAccess W917225955 @default.
- W917225955 hasPrimaryLocation W9172259551 @default.
- W917225955 hasRelatedWork W147003557 @default.
- W917225955 hasRelatedWork W1968524744 @default.
- W917225955 hasRelatedWork W2106552479 @default.
- W917225955 hasRelatedWork W2156581516 @default.
- W917225955 hasRelatedWork W2160863970 @default.
- W917225955 hasRelatedWork W2181765516 @default.
- W917225955 hasRelatedWork W2187344240 @default.
- W917225955 hasRelatedWork W2233980831 @default.
- W917225955 hasRelatedWork W2269908581 @default.
- W917225955 hasRelatedWork W2788763169 @default.
- W917225955 hasRelatedWork W2947790759 @default.
- W917225955 hasRelatedWork W2973871753 @default.
- W917225955 hasRelatedWork W3024315430 @default.
- W917225955 hasRelatedWork W3027668807 @default.
- W917225955 hasRelatedWork W3167758927 @default.
- W917225955 hasRelatedWork W432707492 @default.
- W917225955 hasRelatedWork W2186825669 @default.
- W917225955 hasRelatedWork W2828036268 @default.
- W917225955 hasRelatedWork W2929888887 @default.
- W917225955 hasRelatedWork W3142162084 @default.
- W917225955 hasVolume "21" @default.
- W917225955 isParatext "false" @default.
- W917225955 isRetracted "false" @default.
- W917225955 magId "917225955" @default.
- W917225955 workType "article" @default.