Matches in SemOpenAlex for { <https://semopenalex.org/work/W2319453305> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2319453305 endingPage "234" @default.
- W2319453305 startingPage "226" @default.
- W2319453305 abstract "Recurrent neural networks (RNN) have been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN learning is a difficult task, partly because there are many competing and complex hidden units, such as the long short-term memory (LSTM) and the gated recurrent unit (GRU). We propose a gated unit for RNN, named as minimal gated unit (MGU), since it only contains one gate, which is a minimal design among all gated hidden units. The design of MGU benefits from evaluation results on LSTM and GRU in the literature. Experiments on various sequence data show that MGU has comparable accuracy with GRU, but has a simpler structure, fewer parameters, and faster training. Hence, MGU is suitable in RNN's applications. Its simple architecture also means that it is easier to evaluate and tune, and in principle it is easier to study MGU's properties theoretically and empirically." @default.
- W2319453305 created "2016-06-24" @default.
- W2319453305 creator A5005890948 @default.
- W2319453305 creator A5010751143 @default.
- W2319453305 creator A5087158034 @default.
- W2319453305 creator A5090881698 @default.
- W2319453305 date "2016-06-01" @default.
- W2319453305 modified "2023-10-17" @default.
- W2319453305 title "Minimal gated unit for recurrent neural networks" @default.
- W2319453305 cites W1849277567 @default.
- W2319453305 cites W2064675550 @default.
- W2319453305 cites W2079735306 @default.
- W2319453305 cites W2107878631 @default.
- W2319453305 cites W2112796928 @default.
- W2319453305 cites W2116261113 @default.
- W2319453305 doi "https://doi.org/10.1007/s11633-016-1006-2" @default.
- W2319453305 hasPublicationYear "2016" @default.
- W2319453305 type Work @default.
- W2319453305 sameAs 2319453305 @default.
- W2319453305 citedByCount "228" @default.
- W2319453305 countsByYear W23194533052016 @default.
- W2319453305 countsByYear W23194533052017 @default.
- W2319453305 countsByYear W23194533052018 @default.
- W2319453305 countsByYear W23194533052019 @default.
- W2319453305 countsByYear W23194533052020 @default.
- W2319453305 countsByYear W23194533052021 @default.
- W2319453305 countsByYear W23194533052022 @default.
- W2319453305 countsByYear W23194533052023 @default.
- W2319453305 crossrefType "journal-article" @default.
- W2319453305 hasAuthorship W2319453305A5005890948 @default.
- W2319453305 hasAuthorship W2319453305A5010751143 @default.
- W2319453305 hasAuthorship W2319453305A5087158034 @default.
- W2319453305 hasAuthorship W2319453305A5090881698 @default.
- W2319453305 hasBestOaLocation W23194533052 @default.
- W2319453305 hasConcept C111472728 @default.
- W2319453305 hasConcept C119857082 @default.
- W2319453305 hasConcept C122637931 @default.
- W2319453305 hasConcept C127413603 @default.
- W2319453305 hasConcept C138885662 @default.
- W2319453305 hasConcept C145420912 @default.
- W2319453305 hasConcept C147168706 @default.
- W2319453305 hasConcept C154945302 @default.
- W2319453305 hasConcept C201995342 @default.
- W2319453305 hasConcept C2778112365 @default.
- W2319453305 hasConcept C2780451532 @default.
- W2319453305 hasConcept C2780586882 @default.
- W2319453305 hasConcept C33923547 @default.
- W2319453305 hasConcept C41008148 @default.
- W2319453305 hasConcept C50644808 @default.
- W2319453305 hasConcept C54355233 @default.
- W2319453305 hasConcept C86803240 @default.
- W2319453305 hasConceptScore W2319453305C111472728 @default.
- W2319453305 hasConceptScore W2319453305C119857082 @default.
- W2319453305 hasConceptScore W2319453305C122637931 @default.
- W2319453305 hasConceptScore W2319453305C127413603 @default.
- W2319453305 hasConceptScore W2319453305C138885662 @default.
- W2319453305 hasConceptScore W2319453305C145420912 @default.
- W2319453305 hasConceptScore W2319453305C147168706 @default.
- W2319453305 hasConceptScore W2319453305C154945302 @default.
- W2319453305 hasConceptScore W2319453305C201995342 @default.
- W2319453305 hasConceptScore W2319453305C2778112365 @default.
- W2319453305 hasConceptScore W2319453305C2780451532 @default.
- W2319453305 hasConceptScore W2319453305C2780586882 @default.
- W2319453305 hasConceptScore W2319453305C33923547 @default.
- W2319453305 hasConceptScore W2319453305C41008148 @default.
- W2319453305 hasConceptScore W2319453305C50644808 @default.
- W2319453305 hasConceptScore W2319453305C54355233 @default.
- W2319453305 hasConceptScore W2319453305C86803240 @default.
- W2319453305 hasIssue "3" @default.
- W2319453305 hasLocation W23194533051 @default.
- W2319453305 hasLocation W23194533052 @default.
- W2319453305 hasOpenAccess W2319453305 @default.
- W2319453305 hasPrimaryLocation W23194533051 @default.
- W2319453305 hasRelatedWork W1585007175 @default.
- W2319453305 hasRelatedWork W1847088711 @default.
- W2319453305 hasRelatedWork W1889624880 @default.
- W2319453305 hasRelatedWork W2953061907 @default.
- W2319453305 hasRelatedWork W2964335273 @default.
- W2319453305 hasRelatedWork W3032952384 @default.
- W2319453305 hasRelatedWork W3034302643 @default.
- W2319453305 hasRelatedWork W3036642985 @default.
- W2319453305 hasRelatedWork W4225394202 @default.
- W2319453305 hasRelatedWork W4298287631 @default.
- W2319453305 hasVolume "13" @default.
- W2319453305 isParatext "false" @default.
- W2319453305 isRetracted "false" @default.
- W2319453305 magId "2319453305" @default.
- W2319453305 workType "article" @default.