FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3040211378> ?p ?o ?g. }

• W3040211378 endingPage "110045" @default.
• W3040211378 startingPage "110045" @default.
• W3040211378 abstract "Abstract Recurrent neurons (and in particular LSTM cells) demonstrated to be efficient when used as basic blocks to build sequence to sequence architectures, which represent the state-of-the-art approach in many sequential tasks related to natural language processing. In this work, these architectures are proposed as general purposes, multi-step predictors for nonlinear time series. We analyze artificial, noise-free data generated by chaotic oscillators and compare LSTM nets with the benchmarks set by feed-forward, one-step-recursive and multi-output predictors. We focus on two different training methods for LSTM nets. The traditional one makes use of the so-called teacher forcing, i.e. the ground truth data are used as input for each time step ahead, rather than the outputs predicted for the previous steps. Conversely, the second feeds the previous predictions back into the recurrent neurons, as it happens when the network is used in forecasting. LSTM predictors robustly show the strengths of the two benchmark competitors, i.e., the good short-term performance of one-step-recursive predictors and greatly improved mid-long-term predictions with respect to feed-forward, multi-output predictors. Training LSTM predictors without teacher forcing is recommended to improve accuracy and robustness, and ensures a more uniform distribution of the predictive power within the chaotic attractor. We also show that LSTM architectures maintain good performances when the number of time lags included in the input differs from the actual embedding dimension of the dataset, a feature that is very important when working on real data." @default.
• W3040211378 created "2020-07-10" @default.
• W3040211378 creator A5055447277 @default.
• W3040211378 creator A5069148682 @default.
• W3040211378 date "2020-10-01" @default.
• W3040211378 modified "2023-10-18" @default.
• W3040211378 title "Robustness of LSTM neural networks for multi-step forecasting of chaotic time series" @default.
• W3040211378 cites W1967429206 @default.
• W3040211378 cites W1973071104 @default.
• W3040211378 cites W1984121031 @default.
• W3040211378 cites W1995455153 @default.
• W3040211378 cites W2000061362 @default.
• W3040211378 cites W2002789414 @default.
• W3040211378 cites W2003545651 @default.
• W3040211378 cites W2005607935 @default.
• W3040211378 cites W2009684895 @default.
• W3040211378 cites W2015112229 @default.
• W3040211378 cites W2016589492 @default.
• W3040211378 cites W2017768583 @default.
• W3040211378 cites W2026241078 @default.
• W3040211378 cites W2029896475 @default.
• W3040211378 cites W2031365860 @default.
• W3040211378 cites W2034099719 @default.
• W3040211378 cites W2061570524 @default.
• W3040211378 cites W2064675550 @default.
• W3040211378 cites W2066366061 @default.
• W3040211378 cites W2075234193 @default.
• W3040211378 cites W2083357246 @default.
• W3040211378 cites W2085084764 @default.
• W3040211378 cites W2117148432 @default.
• W3040211378 cites W2118756059 @default.
• W3040211378 cites W2124295615 @default.
• W3040211378 cites W2132156178 @default.
• W3040211378 cites W2132638958 @default.
• W3040211378 cites W2136271007 @default.
• W3040211378 cites W2138484437 @default.
• W3040211378 cites W2149140400 @default.
• W3040211378 cites W2161913203 @default.
• W3040211378 cites W2165562590 @default.
• W3040211378 cites W2605288757 @default.
• W3040211378 cites W2609501756 @default.
• W3040211378 cites W2655594332 @default.
• W3040211378 cites W2765128778 @default.
• W3040211378 cites W2782714865 @default.
• W3040211378 cites W2785760623 @default.
• W3040211378 cites W2794371820 @default.
• W3040211378 cites W2807301194 @default.
• W3040211378 cites W2808720320 @default.
• W3040211378 cites W2912529252 @default.
• W3040211378 cites W2924007269 @default.
• W3040211378 cites W2935233765 @default.
• W3040211378 cites W2949675440 @default.
• W3040211378 cites W2950309905 @default.
• W3040211378 cites W2959676983 @default.
• W3040211378 cites W2976146814 @default.
• W3040211378 cites W2982612860 @default.
• W3040211378 cites W3009718499 @default.
• W3040211378 cites W3012621877 @default.
• W3040211378 cites W3014473050 @default.
• W3040211378 cites W3101544609 @default.
• W3040211378 cites W3101723138 @default.
• W3040211378 cites W3103791812 @default.
• W3040211378 cites W3105919389 @default.
• W3040211378 cites W3156197838 @default.
• W3040211378 cites W1487034709 @default.
• W3040211378 doi "https://doi.org/10.1016/j.chaos.2020.110045" @default.
• W3040211378 hasPublicationYear "2020" @default.
• W3040211378 type Work @default.
• W3040211378 sameAs 3040211378 @default.
• W3040211378 citedByCount "91" @default.
• W3040211378 countsByYear W30402113782019 @default.
• W3040211378 countsByYear W30402113782020 @default.
• W3040211378 countsByYear W30402113782021 @default.
• W3040211378 countsByYear W30402113782022 @default.
• W3040211378 countsByYear W30402113782023 @default.
• W3040211378 crossrefType "journal-article" @default.
• W3040211378 hasAuthorship W3040211378A5055447277 @default.
• W3040211378 hasAuthorship W3040211378A5069148682 @default.
• W3040211378 hasConcept C104317684 @default.
• W3040211378 hasConcept C11413529 @default.
• W3040211378 hasConcept C119857082 @default.
• W3040211378 hasConcept C127313418 @default.
• W3040211378 hasConcept C143724316 @default.
• W3040211378 hasConcept C151406439 @default.
• W3040211378 hasConcept C151730666 @default.
• W3040211378 hasConcept C154945302 @default.
• W3040211378 hasConcept C185592680 @default.
• W3040211378 hasConcept C2775924081 @default.
• W3040211378 hasConcept C2777052490 @default.
• W3040211378 hasConcept C28826006 @default.
• W3040211378 hasConcept C33923547 @default.
• W3040211378 hasConcept C41008148 @default.
• W3040211378 hasConcept C47446073 @default.
• W3040211378 hasConcept C50644808 @default.
• W3040211378 hasConcept C55493867 @default.
• W3040211378 hasConcept C63479239 @default.
• W3040211378 hasConceptScore W3040211378C104317684 @default.
• W3040211378 hasConceptScore W3040211378C11413529 @default.

• next