Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950826612> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2950826612 abstract "Recently recurrent neural networks (RNN) has been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN is a difficult task, partly because there are many competing and complex hidden units (such as LSTM and 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.
- W2950826612 created "2019-06-27" @default.
- W2950826612 creator A5005890948 @default.
- W2950826612 creator A5010751143 @default.
- W2950826612 creator A5087158034 @default.
- W2950826612 creator A5090881698 @default.
- W2950826612 date "2016-03-30" @default.
- W2950826612 modified "2023-09-25" @default.
- W2950826612 title "Minimal Gated Unit for Recurrent Neural Networks" @default.
- W2950826612 cites W2950635152 @default.
- W2950826612 doi "https://doi.org/10.48550/arxiv.1603.09420" @default.
- W2950826612 hasPublicationYear "2016" @default.
- W2950826612 type Work @default.
- W2950826612 sameAs 2950826612 @default.
- W2950826612 citedByCount "7" @default.
- W2950826612 countsByYear W29508266122016 @default.
- W2950826612 countsByYear W29508266122017 @default.
- W2950826612 countsByYear W29508266122018 @default.
- W2950826612 countsByYear W29508266122020 @default.
- W2950826612 countsByYear W29508266122021 @default.
- W2950826612 crossrefType "posted-content" @default.
- W2950826612 hasAuthorship W2950826612A5005890948 @default.
- W2950826612 hasAuthorship W2950826612A5010751143 @default.
- W2950826612 hasAuthorship W2950826612A5087158034 @default.
- W2950826612 hasAuthorship W2950826612A5090881698 @default.
- W2950826612 hasBestOaLocation W29508266121 @default.
- W2950826612 hasConcept C111472728 @default.
- W2950826612 hasConcept C119857082 @default.
- W2950826612 hasConcept C122637931 @default.
- W2950826612 hasConcept C127413603 @default.
- W2950826612 hasConcept C138885662 @default.
- W2950826612 hasConcept C145420912 @default.
- W2950826612 hasConcept C147168706 @default.
- W2950826612 hasConcept C154945302 @default.
- W2950826612 hasConcept C185592680 @default.
- W2950826612 hasConcept C201995342 @default.
- W2950826612 hasConcept C2778112365 @default.
- W2950826612 hasConcept C2780451532 @default.
- W2950826612 hasConcept C2780586882 @default.
- W2950826612 hasConcept C33923547 @default.
- W2950826612 hasConcept C41008148 @default.
- W2950826612 hasConcept C50644808 @default.
- W2950826612 hasConcept C55493867 @default.
- W2950826612 hasConceptScore W2950826612C111472728 @default.
- W2950826612 hasConceptScore W2950826612C119857082 @default.
- W2950826612 hasConceptScore W2950826612C122637931 @default.
- W2950826612 hasConceptScore W2950826612C127413603 @default.
- W2950826612 hasConceptScore W2950826612C138885662 @default.
- W2950826612 hasConceptScore W2950826612C145420912 @default.
- W2950826612 hasConceptScore W2950826612C147168706 @default.
- W2950826612 hasConceptScore W2950826612C154945302 @default.
- W2950826612 hasConceptScore W2950826612C185592680 @default.
- W2950826612 hasConceptScore W2950826612C201995342 @default.
- W2950826612 hasConceptScore W2950826612C2778112365 @default.
- W2950826612 hasConceptScore W2950826612C2780451532 @default.
- W2950826612 hasConceptScore W2950826612C2780586882 @default.
- W2950826612 hasConceptScore W2950826612C33923547 @default.
- W2950826612 hasConceptScore W2950826612C41008148 @default.
- W2950826612 hasConceptScore W2950826612C50644808 @default.
- W2950826612 hasConceptScore W2950826612C55493867 @default.
- W2950826612 hasLocation W29508266121 @default.
- W2950826612 hasOpenAccess W2950826612 @default.
- W2950826612 hasPrimaryLocation W29508266121 @default.
- W2950826612 hasRelatedWork W2793022090 @default.
- W2950826612 hasRelatedWork W2919358988 @default.
- W2950826612 hasRelatedWork W2996568036 @default.
- W2950826612 hasRelatedWork W4213142596 @default.
- W2950826612 hasRelatedWork W4281386417 @default.
- W2950826612 hasRelatedWork W4298168912 @default.
- W2950826612 hasRelatedWork W4327531511 @default.
- W2950826612 hasRelatedWork W4327831767 @default.
- W2950826612 hasRelatedWork W4366674482 @default.
- W2950826612 hasRelatedWork W1629725936 @default.
- W2950826612 isParatext "false" @default.
- W2950826612 isRetracted "false" @default.
- W2950826612 magId "2950826612" @default.
- W2950826612 workType "article" @default.