Matches in SemOpenAlex for { <https://semopenalex.org/work/W2170658049> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2170658049 abstract "Results are presented that suggest that it is possible to learn the architecture of neural networks for speech recognition systems. The Tempo 2 algorithm is proposed. It is a training algorithm for neural networks that trains the temporal parameters of the network (delays and widths of the input windows) as well as the weights. A comparison of the performances with one adaptive parameter set (either weights, delays or widths) shows that the main parameters are the weights. Delays and widths seem to be of lesser importance, but in combination with the weights the temporal parameters can improve performance, especially generalization. A Tempo 2 network with trained delays and widths and random weights can classify 70% of the phonemes correctly. The application to phoneme classification, shows that this adaptive architecture can approach the performance of a carefully hand-tuned TDNN (time-delay neural network) and leads to more compact networks.< <ETX xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>></ETX>" @default.
- W2170658049 created "2016-06-24" @default.
- W2170658049 creator A5007526409 @default.
- W2170658049 creator A5066592814 @default.
- W2170658049 date "1991-01-01" @default.
- W2170658049 modified "2023-09-24" @default.
- W2170658049 title "Learning the architecture of neural networks for speech recognition" @default.
- W2170658049 cites W1530666108 @default.
- W2170658049 cites W2048060899 @default.
- W2170658049 cites W2056009950 @default.
- W2170658049 cites W2070849251 @default.
- W2170658049 cites W2109779438 @default.
- W2170658049 cites W2117671523 @default.
- W2170658049 cites W2167462730 @default.
- W2170658049 cites W2169163929 @default.
- W2170658049 cites W2295027001 @default.
- W2170658049 cites W2766736793 @default.
- W2170658049 doi "https://doi.org/10.1109/icassp.1991.150292" @default.
- W2170658049 hasPublicationYear "1991" @default.
- W2170658049 type Work @default.
- W2170658049 sameAs 2170658049 @default.
- W2170658049 citedByCount "8" @default.
- W2170658049 countsByYear W21706580492014 @default.
- W2170658049 crossrefType "proceedings-article" @default.
- W2170658049 hasAuthorship W2170658049A5007526409 @default.
- W2170658049 hasAuthorship W2170658049A5066592814 @default.
- W2170658049 hasConcept C123657996 @default.
- W2170658049 hasConcept C134306372 @default.
- W2170658049 hasConcept C142362112 @default.
- W2170658049 hasConcept C153180895 @default.
- W2170658049 hasConcept C153349607 @default.
- W2170658049 hasConcept C154945302 @default.
- W2170658049 hasConcept C175202392 @default.
- W2170658049 hasConcept C177148314 @default.
- W2170658049 hasConcept C177264268 @default.
- W2170658049 hasConcept C199360897 @default.
- W2170658049 hasConcept C28490314 @default.
- W2170658049 hasConcept C33923547 @default.
- W2170658049 hasConcept C41008148 @default.
- W2170658049 hasConcept C50644808 @default.
- W2170658049 hasConceptScore W2170658049C123657996 @default.
- W2170658049 hasConceptScore W2170658049C134306372 @default.
- W2170658049 hasConceptScore W2170658049C142362112 @default.
- W2170658049 hasConceptScore W2170658049C153180895 @default.
- W2170658049 hasConceptScore W2170658049C153349607 @default.
- W2170658049 hasConceptScore W2170658049C154945302 @default.
- W2170658049 hasConceptScore W2170658049C175202392 @default.
- W2170658049 hasConceptScore W2170658049C177148314 @default.
- W2170658049 hasConceptScore W2170658049C177264268 @default.
- W2170658049 hasConceptScore W2170658049C199360897 @default.
- W2170658049 hasConceptScore W2170658049C28490314 @default.
- W2170658049 hasConceptScore W2170658049C33923547 @default.
- W2170658049 hasConceptScore W2170658049C41008148 @default.
- W2170658049 hasConceptScore W2170658049C50644808 @default.
- W2170658049 hasLocation W21706580491 @default.
- W2170658049 hasOpenAccess W2170658049 @default.
- W2170658049 hasPrimaryLocation W21706580491 @default.
- W2170658049 hasRelatedWork W1844831382 @default.
- W2170658049 hasRelatedWork W1865113136 @default.
- W2170658049 hasRelatedWork W2018769829 @default.
- W2170658049 hasRelatedWork W2027403964 @default.
- W2170658049 hasRelatedWork W2064784815 @default.
- W2170658049 hasRelatedWork W2075911564 @default.
- W2170658049 hasRelatedWork W2083216547 @default.
- W2170658049 hasRelatedWork W2096093374 @default.
- W2170658049 hasRelatedWork W2106224199 @default.
- W2170658049 hasRelatedWork W2109064010 @default.
- W2170658049 hasRelatedWork W2110055231 @default.
- W2170658049 hasRelatedWork W2110485445 @default.
- W2170658049 hasRelatedWork W2132755896 @default.
- W2170658049 hasRelatedWork W2139232801 @default.
- W2170658049 hasRelatedWork W2140618259 @default.
- W2170658049 hasRelatedWork W2145774052 @default.
- W2170658049 hasRelatedWork W2150034595 @default.
- W2170658049 hasRelatedWork W2158825478 @default.
- W2170658049 hasRelatedWork W2355835431 @default.
- W2170658049 hasRelatedWork W1975223937 @default.
- W2170658049 isParatext "false" @default.
- W2170658049 isRetracted "false" @default.
- W2170658049 magId "2170658049" @default.
- W2170658049 workType "article" @default.