Matches in SemOpenAlex for { <https://semopenalex.org/work/W2021774695> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2021774695 endingPage "61" @default.
- W2021774695 startingPage "35" @default.
- W2021774695 abstract "A learning procedure, called back-propagation, for layered networks of deterministic, neuron-like units has been described previously. The ability of the procedure automatically to discover useful internal representations makes it a powerful tool for attacking difficult problems like speech recognition. This paper describes further research on the learning procedure and presents an example in which a network learns a set of filters that enable it to discriminate formant-like patterns in the presence of noise. The generality of the learning procedure is illustrated by a second example in which a similar network learns an edge detection task. The speed of learning is strongly dependent on the shape of the surface formed by the error measure in “weight space”. Examples are given of the error surface for a simple task and an acceleration method that speeds up descent in weight space is illustrated. The main drawback of the learning procedure is the way it scales as the size of the task and the network increases. Some preliminary results on scaling are reported and it is shown how the magnitude of the optimal weight changes depends on the fan-in of the units. Additional results show how the amount of interaction between the weights affects the learning speed. The paper is concluded with a discussion of the difficulties that are likely to be encounted in applying back-propagation to more realistic problems in speech recognition, and some promising approaches to overcoming these difficulties." @default.
- W2021774695 created "2016-06-24" @default.
- W2021774695 creator A5015410454 @default.
- W2021774695 creator A5024209719 @default.
- W2021774695 date "1987-03-01" @default.
- W2021774695 modified "2023-10-16" @default.
- W2021774695 title "Learning sets of filters using back-propagation" @default.
- W2021774695 cites W1498436455 @default.
- W2021774695 cites W1995169133 @default.
- W2021774695 cites W2010581677 @default.
- W2021774695 cites W2042492924 @default.
- W2021774695 cites W2155487652 @default.
- W2021774695 doi "https://doi.org/10.1016/0885-2308(87)90026-x" @default.
- W2021774695 hasPublicationYear "1987" @default.
- W2021774695 type Work @default.
- W2021774695 sameAs 2021774695 @default.
- W2021774695 citedByCount "106" @default.
- W2021774695 countsByYear W20217746952012 @default.
- W2021774695 countsByYear W20217746952013 @default.
- W2021774695 countsByYear W20217746952014 @default.
- W2021774695 countsByYear W20217746952015 @default.
- W2021774695 countsByYear W20217746952016 @default.
- W2021774695 countsByYear W20217746952017 @default.
- W2021774695 countsByYear W20217746952019 @default.
- W2021774695 countsByYear W20217746952020 @default.
- W2021774695 countsByYear W20217746952021 @default.
- W2021774695 countsByYear W20217746952022 @default.
- W2021774695 crossrefType "journal-article" @default.
- W2021774695 hasAuthorship W2021774695A5015410454 @default.
- W2021774695 hasAuthorship W2021774695A5024209719 @default.
- W2021774695 hasBestOaLocation W20217746952 @default.
- W2021774695 hasConcept C11413529 @default.
- W2021774695 hasConcept C115961682 @default.
- W2021774695 hasConcept C153180895 @default.
- W2021774695 hasConcept C153258448 @default.
- W2021774695 hasConcept C154945302 @default.
- W2021774695 hasConcept C155032097 @default.
- W2021774695 hasConcept C15744967 @default.
- W2021774695 hasConcept C162324750 @default.
- W2021774695 hasConcept C177264268 @default.
- W2021774695 hasConcept C187736073 @default.
- W2021774695 hasConcept C199360897 @default.
- W2021774695 hasConcept C2780451532 @default.
- W2021774695 hasConcept C2780767217 @default.
- W2021774695 hasConcept C41008148 @default.
- W2021774695 hasConcept C50644808 @default.
- W2021774695 hasConcept C542102704 @default.
- W2021774695 hasConcept C99498987 @default.
- W2021774695 hasConceptScore W2021774695C11413529 @default.
- W2021774695 hasConceptScore W2021774695C115961682 @default.
- W2021774695 hasConceptScore W2021774695C153180895 @default.
- W2021774695 hasConceptScore W2021774695C153258448 @default.
- W2021774695 hasConceptScore W2021774695C154945302 @default.
- W2021774695 hasConceptScore W2021774695C155032097 @default.
- W2021774695 hasConceptScore W2021774695C15744967 @default.
- W2021774695 hasConceptScore W2021774695C162324750 @default.
- W2021774695 hasConceptScore W2021774695C177264268 @default.
- W2021774695 hasConceptScore W2021774695C187736073 @default.
- W2021774695 hasConceptScore W2021774695C199360897 @default.
- W2021774695 hasConceptScore W2021774695C2780451532 @default.
- W2021774695 hasConceptScore W2021774695C2780767217 @default.
- W2021774695 hasConceptScore W2021774695C41008148 @default.
- W2021774695 hasConceptScore W2021774695C50644808 @default.
- W2021774695 hasConceptScore W2021774695C542102704 @default.
- W2021774695 hasConceptScore W2021774695C99498987 @default.
- W2021774695 hasIssue "1" @default.
- W2021774695 hasLocation W20217746951 @default.
- W2021774695 hasLocation W20217746952 @default.
- W2021774695 hasOpenAccess W2021774695 @default.
- W2021774695 hasPrimaryLocation W20217746951 @default.
- W2021774695 hasRelatedWork W1495379181 @default.
- W2021774695 hasRelatedWork W1539246760 @default.
- W2021774695 hasRelatedWork W2115605526 @default.
- W2021774695 hasRelatedWork W2157746493 @default.
- W2021774695 hasRelatedWork W2371065793 @default.
- W2021774695 hasRelatedWork W2786746258 @default.
- W2021774695 hasRelatedWork W2788727425 @default.
- W2021774695 hasRelatedWork W2894173309 @default.
- W2021774695 hasRelatedWork W3093883775 @default.
- W2021774695 hasRelatedWork W4225893763 @default.
- W2021774695 hasVolume "2" @default.
- W2021774695 isParatext "false" @default.
- W2021774695 isRetracted "false" @default.
- W2021774695 magId "2021774695" @default.
- W2021774695 workType "article" @default.