FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912348464> ?p ?o ?g. }

• W2912348464 abstract "Despite the recent popularity of deep generative state space models, few comparisons have been made between network architectures and the inference steps of the Bayesian filtering framework -- with most models simultaneously approximating both state transition and update steps with a single recurrent neural network (RNN). In this paper, we introduce the Recurrent Neural Filter (RNF), a novel recurrent autoencoder architecture that learns distinct representations for each Bayesian filtering step, captured by a series of encoders and decoders. Testing this on three real-world time series datasets, we demonstrate that the decoupled representations learnt not only improve the accuracy of one-step-ahead forecasts while providing realistic uncertainty estimates, but also facilitate multistep prediction through the separation of encoder stages." @default.
• W2912348464 created "2019-02-21" @default.
• W2912348464 creator A5011437628 @default.
• W2912348464 creator A5058617210 @default.
• W2912348464 creator A5090331439 @default.
• W2912348464 date "2019-01-23" @default.
• W2912348464 modified "2023-09-27" @default.
• W2912348464 title "Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction" @default.
• W2912348464 cites W1508886855 @default.
• W2912348464 cites W1542912205 @default.
• W2912348464 cites W1547716228 @default.
• W2912348464 cites W170770739 @default.
• W2912348464 cites W1959608418 @default.
• W2912348464 cites W1972508593 @default.
• W2912348464 cites W1999479532 @default.
• W2912348464 cites W1999726465 @default.
• W2912348464 cites W2008089260 @default.
• W2912348464 cites W2020934227 @default.
• W2912348464 cites W2053530354 @default.
• W2912348464 cites W2064675550 @default.
• W2912348464 cites W2105934661 @default.
• W2912348464 cites W2146399390 @default.
• W2912348464 cites W2176035349 @default.
• W2912348464 cites W2210838531 @default.
• W2912348464 cites W2464234964 @default.
• W2912348464 cites W2519091744 @default.
• W2912348464 cites W2571446175 @default.
• W2912348464 cites W2607045400 @default.
• W2912348464 cites W2619010835 @default.
• W2912348464 cites W2626778328 @default.
• W2912348464 cites W2745007981 @default.
• W2912348464 cites W2750941309 @default.
• W2912348464 cites W2753738274 @default.
• W2912348464 cites W2773625660 @default.
• W2912348464 cites W2787365188 @default.
• W2912348464 cites W2787723410 @default.
• W2912348464 cites W2789062658 @default.
• W2912348464 cites W2794449215 @default.
• W2912348464 cites W2889928394 @default.
• W2912348464 cites W2891583400 @default.
• W2912348464 cites W2910135751 @default.
• W2912348464 cites W2950662112 @default.
• W2912348464 cites W2962695963 @default.
• W2912348464 cites W2962738009 @default.
• W2912348464 cites W2962824919 @default.
• W2912348464 cites W2963074410 @default.
• W2912348464 cites W2963104724 @default.
• W2912348464 cites W2963166838 @default.
• W2912348464 cites W2963264829 @default.
• W2912348464 cites W2963285578 @default.
• W2912348464 cites W2963305465 @default.
• W2912348464 cites W2963521490 @default.
• W2912348464 cites W2963524109 @default.
• W2912348464 cites W2963799213 @default.
• W2912348464 cites W2964110616 @default.
• W2912348464 cites W2964232608 @default.
• W2912348464 cites W3093010610 @default.
• W2912348464 cites W3121364726 @default.
• W2912348464 cites W3122879523 @default.
• W2912348464 cites W592244745 @default.
• W2912348464 cites W635291686 @default.
• W2912348464 cites W88520345 @default.
• W2912348464 hasPublicationYear "2019" @default.
• W2912348464 type Work @default.
• W2912348464 sameAs 2912348464 @default.
• W2912348464 citedByCount "6" @default.
• W2912348464 countsByYear W29123484642019 @default.
• W2912348464 countsByYear W29123484642020 @default.
• W2912348464 countsByYear W29123484642021 @default.
• W2912348464 crossrefType "posted-content" @default.
• W2912348464 hasAuthorship W2912348464A5011437628 @default.
• W2912348464 hasAuthorship W2912348464A5058617210 @default.
• W2912348464 hasAuthorship W2912348464A5090331439 @default.
• W2912348464 hasConcept C101738243 @default.
• W2912348464 hasConcept C105795698 @default.
• W2912348464 hasConcept C106131492 @default.
• W2912348464 hasConcept C107673813 @default.
• W2912348464 hasConcept C108583219 @default.
• W2912348464 hasConcept C111919701 @default.
• W2912348464 hasConcept C11413529 @default.
• W2912348464 hasConcept C118505674 @default.
• W2912348464 hasConcept C119857082 @default.
• W2912348464 hasConcept C143724316 @default.
• W2912348464 hasConcept C147168706 @default.
• W2912348464 hasConcept C151406439 @default.
• W2912348464 hasConcept C151730666 @default.
• W2912348464 hasConcept C153180895 @default.
• W2912348464 hasConcept C154945302 @default.
• W2912348464 hasConcept C157286648 @default.
• W2912348464 hasConcept C160234255 @default.
• W2912348464 hasConcept C2776214188 @default.
• W2912348464 hasConcept C31972630 @default.
• W2912348464 hasConcept C33923547 @default.
• W2912348464 hasConcept C41008148 @default.
• W2912348464 hasConcept C48103436 @default.
• W2912348464 hasConcept C50644808 @default.
• W2912348464 hasConcept C52421305 @default.
• W2912348464 hasConcept C72434380 @default.
• W2912348464 hasConcept C86803240 @default.
• W2912348464 hasConceptScore W2912348464C101738243 @default.

• next