FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3160909062> ?p ?o ?g. }

• W3160909062 endingPage "268" @default.
• W3160909062 startingPage "252" @default.
• W3160909062 abstract "An approach to the time-accurate prediction of chaotic solutions is by learning temporal patterns from data. Echo State Networks (ESNs), which are a class of Reservoir Computing, can accurately predict the chaotic dynamics well beyond the predictability time. Existing studies, however, also showed that small changes in the hyperparameters may markedly affect the network's performance. The overarching aim of this paper is to improve the robustness in the selection of hyperparameters in Echo State Networks for the time-accurate prediction of chaotic solutions. We define the robustness of a validation strategy as its ability to select hyperparameters that perform consistently between validation and test sets. The goal is three-fold. First, we investigate routinely used validation strategies. Second, we propose the Recycle Validation, and the chaotic versions of existing validation strategies, to specifically tackle the forecasting of chaotic systems. Third, we compare Bayesian optimization with the traditional grid search for optimal hyperparameter selection. Numerical tests are performed on prototypical nonlinear systems that have chaotic and quasiperiodic solutions, such as the Lorenz and Lorenz-96 systems, and the Kuznetsov oscillator. Both model-free and model-informed Echo State Networks are analysed. By comparing the networks' performance in learning chaotic (unpredictable) versus quasiperiodic (predictable) solutions, we highlight fundamental challenges in learning chaotic solutions. The proposed validation strategies, which are based on the dynamical systems properties of chaotic time series, are shown to outperform the state-of-the-art validation strategies. Because the strategies are principled - they are based on chaos theory such as the Lyapunov time - they can be applied to other Recurrent Neural Networks architectures with little modification. This work opens up new possibilities for the robust design and application of Echo State Networks, and Recurrent Neural Networks, to the time-accurate prediction of chaotic systems." @default.
• W3160909062 created "2021-05-24" @default.
• W3160909062 creator A5081561708 @default.
• W3160909062 creator A5082150294 @default.
• W3160909062 date "2021-10-01" @default.
• W3160909062 modified "2023-10-18" @default.
• W3160909062 title "Robust Optimization and Validation of Echo State Networks for learning chaotic dynamics" @default.
• W3160909062 cites W1036981403 @default.
• W3160909062 cites W1498436455 @default.
• W3160909062 cites W1508379405 @default.
• W3160909062 cites W1970105125 @default.
• W3160909062 cites W1970396034 @default.
• W3160909062 cites W1971129545 @default.
• W3160909062 cites W1989312953 @default.
• W3160909062 cites W2027893048 @default.
• W3160909062 cites W2039118235 @default.
• W3160909062 cites W2051989995 @default.
• W3160909062 cites W2063419567 @default.
• W3160909062 cites W2064675550 @default.
• W3160909062 cites W2078483536 @default.
• W3160909062 cites W2103179919 @default.
• W3160909062 cites W2107878631 @default.
• W3160909062 cites W2118706537 @default.
• W3160909062 cites W2126062496 @default.
• W3160909062 cites W2141394518 @default.
• W3160909062 cites W2150355110 @default.
• W3160909062 cites W2164454345 @default.
• W3160909062 cites W2605288757 @default.
• W3160909062 cites W2758692923 @default.
• W3160909062 cites W2765128778 @default.
• W3160909062 cites W2782714865 @default.
• W3160909062 cites W2808720320 @default.
• W3160909062 cites W2852240488 @default.
• W3160909062 cites W2898436200 @default.
• W3160909062 cites W2921881408 @default.
• W3160909062 cites W2959676983 @default.
• W3160909062 cites W2963003308 @default.
• W3160909062 cites W2963268903 @default.
• W3160909062 cites W2982612860 @default.
• W3160909062 cites W3012621877 @default.
• W3160909062 cites W3099878876 @default.
• W3160909062 cites W3101235239 @default.
• W3160909062 cites W3101544609 @default.
• W3160909062 cites W3101766586 @default.
• W3160909062 cites W3102140816 @default.
• W3160909062 cites W3102502580 @default.
• W3160909062 cites W3103145119 @default.
• W3160909062 cites W3128485317 @default.
• W3160909062 cites W4251274027 @default.
• W3160909062 doi "https://doi.org/10.1016/j.neunet.2021.05.004" @default.
• W3160909062 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34034072" @default.
• W3160909062 hasPublicationYear "2021" @default.
• W3160909062 type Work @default.
• W3160909062 sameAs 3160909062 @default.
• W3160909062 citedByCount "25" @default.
• W3160909062 countsByYear W31609090622021 @default.
• W3160909062 countsByYear W31609090622022 @default.
• W3160909062 countsByYear W31609090622023 @default.
• W3160909062 crossrefType "journal-article" @default.
• W3160909062 hasAuthorship W3160909062A5081561708 @default.
• W3160909062 hasAuthorship W3160909062A5082150294 @default.
• W3160909062 hasBestOaLocation W31609090622 @default.
• W3160909062 hasConcept C104317684 @default.
• W3160909062 hasConcept C10485038 @default.
• W3160909062 hasConcept C105795698 @default.
• W3160909062 hasConcept C119857082 @default.
• W3160909062 hasConcept C12267149 @default.
• W3160909062 hasConcept C134306372 @default.
• W3160909062 hasConcept C135796866 @default.
• W3160909062 hasConcept C147168706 @default.
• W3160909062 hasConcept C151510863 @default.
• W3160909062 hasConcept C154945302 @default.
• W3160909062 hasConcept C172025690 @default.
• W3160909062 hasConcept C185592680 @default.
• W3160909062 hasConcept C197640229 @default.
• W3160909062 hasConcept C2777052490 @default.
• W3160909062 hasConcept C33923547 @default.
• W3160909062 hasConcept C41008148 @default.
• W3160909062 hasConcept C50644808 @default.
• W3160909062 hasConcept C55493867 @default.
• W3160909062 hasConcept C55637507 @default.
• W3160909062 hasConcept C63479239 @default.
• W3160909062 hasConcept C8642999 @default.
• W3160909062 hasConceptScore W3160909062C104317684 @default.
• W3160909062 hasConceptScore W3160909062C10485038 @default.
• W3160909062 hasConceptScore W3160909062C105795698 @default.
• W3160909062 hasConceptScore W3160909062C119857082 @default.
• W3160909062 hasConceptScore W3160909062C12267149 @default.
• W3160909062 hasConceptScore W3160909062C134306372 @default.
• W3160909062 hasConceptScore W3160909062C135796866 @default.
• W3160909062 hasConceptScore W3160909062C147168706 @default.
• W3160909062 hasConceptScore W3160909062C151510863 @default.
• W3160909062 hasConceptScore W3160909062C154945302 @default.
• W3160909062 hasConceptScore W3160909062C172025690 @default.
• W3160909062 hasConceptScore W3160909062C185592680 @default.
• W3160909062 hasConceptScore W3160909062C197640229 @default.
• W3160909062 hasConceptScore W3160909062C2777052490 @default.
• W3160909062 hasConceptScore W3160909062C33923547 @default.

• next