Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313016919> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4313016919 abstract "The Long Short-Term Memory (LSTM) architecture is one of the most successful types of Recurrent Neural Networks (RNNs). However, the number of parameters that LSTMs need to achieve acceptable performance might be larger than desired for standard devices. In this work, an Extended LSTM (E-LSTM) architecture is proposed to reduce the number of parameters needed to achieve similar performance to LSTMs. The architecture of the proposed E-LSTM is characterized by higher and explicit connectivity between distant past and current cell states' values, increasing the likelihood of a higher information transmission between data points separated by long lags. Analysis of possible nonlinear relations in the data sets aids in the process of determining an appropriate placement of increased connectivity, performed using the Distance Correlation (DC) method. The proposed E-LSTM reduces the number of parameters needed, by an order of magnitude for some cases, with acceptable increases in both CPU time and memory needed for the training process." @default.
- W4313016919 created "2023-01-05" @default.
- W4313016919 creator A5000267488 @default.
- W4313016919 creator A5076951655 @default.
- W4313016919 date "2022-07-18" @default.
- W4313016919 modified "2023-10-17" @default.
- W4313016919 title "E-LSTM: An extension to the LSTM architecture for incorporating long lag dependencies" @default.
- W4313016919 cites W1689711448 @default.
- W4313016919 cites W1951742130 @default.
- W4313016919 cites W1989540221 @default.
- W4313016919 cites W1995245587 @default.
- W4313016919 cites W2064675550 @default.
- W4313016919 cites W2069143585 @default.
- W4313016919 cites W2094673481 @default.
- W4313016919 cites W2107878631 @default.
- W4313016919 cites W2136848157 @default.
- W4313016919 cites W2341332379 @default.
- W4313016919 cites W2399057275 @default.
- W4313016919 cites W2528639018 @default.
- W4313016919 cites W2572939427 @default.
- W4313016919 cites W2581522324 @default.
- W4313016919 cites W2587586954 @default.
- W4313016919 cites W2606722458 @default.
- W4313016919 cites W2632775315 @default.
- W4313016919 cites W2767768852 @default.
- W4313016919 cites W2768950724 @default.
- W4313016919 cites W2770128248 @default.
- W4313016919 cites W2786429113 @default.
- W4313016919 cites W2902499798 @default.
- W4313016919 cites W2951810231 @default.
- W4313016919 cites W2955149191 @default.
- W4313016919 cites W2965981069 @default.
- W4313016919 cites W2979858166 @default.
- W4313016919 cites W2979880198 @default.
- W4313016919 cites W2995306477 @default.
- W4313016919 cites W3015739135 @default.
- W4313016919 cites W3106063097 @default.
- W4313016919 cites W3175818677 @default.
- W4313016919 cites W3178086426 @default.
- W4313016919 doi "https://doi.org/10.1109/ijcnn55064.2022.9892810" @default.
- W4313016919 hasPublicationYear "2022" @default.
- W4313016919 type Work @default.
- W4313016919 citedByCount "1" @default.
- W4313016919 countsByYear W43130169192023 @default.
- W4313016919 crossrefType "proceedings-article" @default.
- W4313016919 hasAuthorship W4313016919A5000267488 @default.
- W4313016919 hasAuthorship W4313016919A5076951655 @default.
- W4313016919 hasConcept C111919701 @default.
- W4313016919 hasConcept C119857082 @default.
- W4313016919 hasConcept C123657996 @default.
- W4313016919 hasConcept C133488467 @default.
- W4313016919 hasConcept C142362112 @default.
- W4313016919 hasConcept C147168706 @default.
- W4313016919 hasConcept C153180895 @default.
- W4313016919 hasConcept C153349607 @default.
- W4313016919 hasConcept C154945302 @default.
- W4313016919 hasConcept C199360897 @default.
- W4313016919 hasConcept C2778029271 @default.
- W4313016919 hasConcept C31258907 @default.
- W4313016919 hasConcept C41008148 @default.
- W4313016919 hasConcept C50644808 @default.
- W4313016919 hasConcept C75778745 @default.
- W4313016919 hasConcept C98045186 @default.
- W4313016919 hasConceptScore W4313016919C111919701 @default.
- W4313016919 hasConceptScore W4313016919C119857082 @default.
- W4313016919 hasConceptScore W4313016919C123657996 @default.
- W4313016919 hasConceptScore W4313016919C133488467 @default.
- W4313016919 hasConceptScore W4313016919C142362112 @default.
- W4313016919 hasConceptScore W4313016919C147168706 @default.
- W4313016919 hasConceptScore W4313016919C153180895 @default.
- W4313016919 hasConceptScore W4313016919C153349607 @default.
- W4313016919 hasConceptScore W4313016919C154945302 @default.
- W4313016919 hasConceptScore W4313016919C199360897 @default.
- W4313016919 hasConceptScore W4313016919C2778029271 @default.
- W4313016919 hasConceptScore W4313016919C31258907 @default.
- W4313016919 hasConceptScore W4313016919C41008148 @default.
- W4313016919 hasConceptScore W4313016919C50644808 @default.
- W4313016919 hasConceptScore W4313016919C75778745 @default.
- W4313016919 hasConceptScore W4313016919C98045186 @default.
- W4313016919 hasFunder F4320314000 @default.
- W4313016919 hasLocation W43130169191 @default.
- W4313016919 hasOpenAccess W4313016919 @default.
- W4313016919 hasPrimaryLocation W43130169191 @default.
- W4313016919 hasRelatedWork W2912153778 @default.
- W4313016919 hasRelatedWork W2912831041 @default.
- W4313016919 hasRelatedWork W2973430807 @default.
- W4313016919 hasRelatedWork W3034576161 @default.
- W4313016919 hasRelatedWork W3173606726 @default.
- W4313016919 hasRelatedWork W4288108708 @default.
- W4313016919 hasRelatedWork W4365935674 @default.
- W4313016919 hasRelatedWork W4385280324 @default.
- W4313016919 hasRelatedWork W4387163678 @default.
- W4313016919 hasRelatedWork W3095342734 @default.
- W4313016919 isParatext "false" @default.
- W4313016919 isRetracted "false" @default.
- W4313016919 workType "article" @default.