Matches in SemOpenAlex for { <https://semopenalex.org/work/W2017006882> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2017006882 endingPage "93" @default.
- W2017006882 startingPage "82" @default.
- W2017006882 abstract "A new neural network and its learning algorithm are proposed. The neural network consists of four layers—input, hidden, output and final output layers. The hidden and output layers are multiple. The proposed learning algorithm is called the SICL (spread pattern information and cooperative learning) method and has the following features: (1) the singular points of back propagation errors in the BP method are removed; (2) a spread pattern information (SI) algorithm is proposed; and (3) a cooperative learning (CL) algorithm is proposed. Using the SICL method, it is possible to learn analog data accurately and to obtain a stable output. Using this neural network, the authors developed a speech production system consisting of a phonemic symbol production subsystem and a speech parameter production subsystem. The system is applied to speech data and the system performance is examined. Especially, for the speech parameter production subsystem, the learning capacity and the optimal area for learning constants are studied. As a result, it is shown that it is possible to learn and produce speech data with high accuracy using the proposed neural network." @default.
- W2017006882 created "2016-06-24" @default.
- W2017006882 creator A5051114781 @default.
- W2017006882 creator A5083340840 @default.
- W2017006882 date "1991-01-01" @default.
- W2017006882 modified "2023-09-26" @default.
- W2017006882 title "Learning and production of speech pattern using multilayer neural networks" @default.
- W2017006882 cites W4300402905 @default.
- W2017006882 doi "https://doi.org/10.1002/scj.4690220309" @default.
- W2017006882 hasPublicationYear "1991" @default.
- W2017006882 type Work @default.
- W2017006882 sameAs 2017006882 @default.
- W2017006882 citedByCount "0" @default.
- W2017006882 crossrefType "journal-article" @default.
- W2017006882 hasAuthorship W2017006882A5051114781 @default.
- W2017006882 hasAuthorship W2017006882A5083340840 @default.
- W2017006882 hasConcept C11413529 @default.
- W2017006882 hasConcept C134400042 @default.
- W2017006882 hasConcept C139719470 @default.
- W2017006882 hasConcept C14999030 @default.
- W2017006882 hasConcept C153180895 @default.
- W2017006882 hasConcept C154945302 @default.
- W2017006882 hasConcept C155032097 @default.
- W2017006882 hasConcept C162324750 @default.
- W2017006882 hasConcept C175202392 @default.
- W2017006882 hasConcept C199360897 @default.
- W2017006882 hasConcept C2778348673 @default.
- W2017006882 hasConcept C28490314 @default.
- W2017006882 hasConcept C41008148 @default.
- W2017006882 hasConcept C50644808 @default.
- W2017006882 hasConceptScore W2017006882C11413529 @default.
- W2017006882 hasConceptScore W2017006882C134400042 @default.
- W2017006882 hasConceptScore W2017006882C139719470 @default.
- W2017006882 hasConceptScore W2017006882C14999030 @default.
- W2017006882 hasConceptScore W2017006882C153180895 @default.
- W2017006882 hasConceptScore W2017006882C154945302 @default.
- W2017006882 hasConceptScore W2017006882C155032097 @default.
- W2017006882 hasConceptScore W2017006882C162324750 @default.
- W2017006882 hasConceptScore W2017006882C175202392 @default.
- W2017006882 hasConceptScore W2017006882C199360897 @default.
- W2017006882 hasConceptScore W2017006882C2778348673 @default.
- W2017006882 hasConceptScore W2017006882C28490314 @default.
- W2017006882 hasConceptScore W2017006882C41008148 @default.
- W2017006882 hasConceptScore W2017006882C50644808 @default.
- W2017006882 hasIssue "3" @default.
- W2017006882 hasLocation W20170068821 @default.
- W2017006882 hasOpenAccess W2017006882 @default.
- W2017006882 hasPrimaryLocation W20170068821 @default.
- W2017006882 hasRelatedWork W2075600602 @default.
- W2017006882 hasRelatedWork W2096049549 @default.
- W2017006882 hasRelatedWork W2104698839 @default.
- W2017006882 hasRelatedWork W2105899231 @default.
- W2017006882 hasRelatedWork W2131836320 @default.
- W2017006882 hasRelatedWork W2362189222 @default.
- W2017006882 hasRelatedWork W2379874775 @default.
- W2017006882 hasRelatedWork W2391384657 @default.
- W2017006882 hasRelatedWork W3048788076 @default.
- W2017006882 hasRelatedWork W2182757990 @default.
- W2017006882 hasVolume "22" @default.
- W2017006882 isParatext "false" @default.
- W2017006882 isRetracted "false" @default.
- W2017006882 magId "2017006882" @default.
- W2017006882 workType "article" @default.