Matches in SemOpenAlex for { <https://semopenalex.org/work/W2149272334> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2149272334 endingPage "1168" @default.
- W2149272334 startingPage "1162" @default.
- W2149272334 abstract "The problems are discussed of the recognition of handprinted and spoken digits and the handprinted and spoken English alphabet. Four such experiments were conducted and the results were compared to a conventional nearest-neighbor classifier trained on the same data. Results indicate that neural networks and nearest-neighbor classifiers perform at near the same level of accuracy. For each task, a critical number of neurons can be determined experimentally which yields highest recognition accuracy with least hardware. This number can also measure the classification efficiency of the input feature encoder. Several techniques for optimizing the performance of layered networks are discussed. A constant level added to the input signal biases patterns into the range where the learning rate is highest. Eliminating near-zero weights after learning results in little loss of accuracy. Finally, a novel handwriting encoder is described.< <ETX xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>></ETX>" @default.
- W2149272334 created "2016-06-24" @default.
- W2149272334 creator A5016148418 @default.
- W2149272334 date "1988-07-01" @default.
- W2149272334 modified "2023-09-27" @default.
- W2149272334 title "Experiments on neural net recognition of spoken and written text" @default.
- W2149272334 cites W1590612169 @default.
- W2149272334 cites W1995341919 @default.
- W2149272334 cites W2009422037 @default.
- W2149272334 cites W2042492924 @default.
- W2149272334 cites W2101927907 @default.
- W2149272334 cites W2120383790 @default.
- W2149272334 cites W2128084896 @default.
- W2149272334 cites W2128160875 @default.
- W2149272334 cites W2165558283 @default.
- W2149272334 cites W2584782119 @default.
- W2149272334 cites W2986470063 @default.
- W2149272334 doi "https://doi.org/10.1109/29.1643" @default.
- W2149272334 hasPublicationYear "1988" @default.
- W2149272334 type Work @default.
- W2149272334 sameAs 2149272334 @default.
- W2149272334 citedByCount "251" @default.
- W2149272334 countsByYear W21492723342012 @default.
- W2149272334 countsByYear W21492723342013 @default.
- W2149272334 countsByYear W21492723342014 @default.
- W2149272334 countsByYear W21492723342015 @default.
- W2149272334 countsByYear W21492723342016 @default.
- W2149272334 countsByYear W21492723342017 @default.
- W2149272334 countsByYear W21492723342018 @default.
- W2149272334 countsByYear W21492723342019 @default.
- W2149272334 countsByYear W21492723342020 @default.
- W2149272334 countsByYear W21492723342021 @default.
- W2149272334 countsByYear W21492723342023 @default.
- W2149272334 crossrefType "journal-article" @default.
- W2149272334 hasAuthorship W2149272334A5016148418 @default.
- W2149272334 hasConcept C111919701 @default.
- W2149272334 hasConcept C112876837 @default.
- W2149272334 hasConcept C113238511 @default.
- W2149272334 hasConcept C118505674 @default.
- W2149272334 hasConcept C138885662 @default.
- W2149272334 hasConcept C153180895 @default.
- W2149272334 hasConcept C154945302 @default.
- W2149272334 hasConcept C2776401178 @default.
- W2149272334 hasConcept C2779386606 @default.
- W2149272334 hasConcept C28490314 @default.
- W2149272334 hasConcept C41008148 @default.
- W2149272334 hasConcept C41895202 @default.
- W2149272334 hasConcept C50644808 @default.
- W2149272334 hasConcept C95623464 @default.
- W2149272334 hasConceptScore W2149272334C111919701 @default.
- W2149272334 hasConceptScore W2149272334C112876837 @default.
- W2149272334 hasConceptScore W2149272334C113238511 @default.
- W2149272334 hasConceptScore W2149272334C118505674 @default.
- W2149272334 hasConceptScore W2149272334C138885662 @default.
- W2149272334 hasConceptScore W2149272334C153180895 @default.
- W2149272334 hasConceptScore W2149272334C154945302 @default.
- W2149272334 hasConceptScore W2149272334C2776401178 @default.
- W2149272334 hasConceptScore W2149272334C2779386606 @default.
- W2149272334 hasConceptScore W2149272334C28490314 @default.
- W2149272334 hasConceptScore W2149272334C41008148 @default.
- W2149272334 hasConceptScore W2149272334C41895202 @default.
- W2149272334 hasConceptScore W2149272334C50644808 @default.
- W2149272334 hasConceptScore W2149272334C95623464 @default.
- W2149272334 hasIssue "7" @default.
- W2149272334 hasLocation W21492723341 @default.
- W2149272334 hasOpenAccess W2149272334 @default.
- W2149272334 hasPrimaryLocation W21492723341 @default.
- W2149272334 hasRelatedWork W1505703478 @default.
- W2149272334 hasRelatedWork W2022996092 @default.
- W2149272334 hasRelatedWork W2086396635 @default.
- W2149272334 hasRelatedWork W2146076056 @default.
- W2149272334 hasRelatedWork W2151973236 @default.
- W2149272334 hasRelatedWork W2158785961 @default.
- W2149272334 hasRelatedWork W2921036759 @default.
- W2149272334 hasRelatedWork W3146836350 @default.
- W2149272334 hasRelatedWork W4242764575 @default.
- W2149272334 hasRelatedWork W3158004940 @default.
- W2149272334 hasVolume "36" @default.
- W2149272334 isParatext "false" @default.
- W2149272334 isRetracted "false" @default.
- W2149272334 magId "2149272334" @default.
- W2149272334 workType "article" @default.