Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288045136> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4288045136 endingPage "84" @default.
- W4288045136 startingPage "75" @default.
- W4288045136 abstract "In this study, we develop a recurrent neural network-induced Gaussian process (RNNGP) to model sequence data. We derive the equivalence between infinitely wide neural networks and Gaussian processes (GPs) for a relaxed recurrent neural network (RNN) with untied weights. We compute the covariance function of the RNNGP using an analytical iteration formula derived through the RNN procedure with an error-function-based activation function. To simplify our discussion, we use the RNNGP to perform Bayesian inference on vanilla RNNs for various problems, such as Modified National Institute of Standards and Technology digit identification, Mackey–Glass time-series forecasting, and lithium-ion battery state-of-health estimation. The results demonstrate the flexibility of the RNNGP in modeling sequence data. Furthermore, the RNNGP predictions typically outperform those of the original RNNs and GPs, demonstrating the efficiency of the RNNGP as a data-driven model. Moreover, the RNNGP can quantify the uncertainty in the predictions, which implies the significant potential of the RNNGP in uncertainty quantification analyses." @default.
- W4288045136 created "2022-07-27" @default.
- W4288045136 creator A5048704738 @default.
- W4288045136 creator A5067483266 @default.
- W4288045136 creator A5071080919 @default.
- W4288045136 date "2022-10-01" @default.
- W4288045136 modified "2023-10-03" @default.
- W4288045136 title "Recurrent neural network-induced Gaussian process" @default.
- W4288045136 cites W1994504172 @default.
- W4288045136 cites W2064675550 @default.
- W4288045136 cites W2078279667 @default.
- W4288045136 cites W2094631910 @default.
- W4288045136 cites W2112796928 @default.
- W4288045136 cites W2588649990 @default.
- W4288045136 cites W2811199191 @default.
- W4288045136 cites W2914713740 @default.
- W4288045136 cites W2962942717 @default.
- W4288045136 cites W2996610370 @default.
- W4288045136 cites W3002102497 @default.
- W4288045136 doi "https://doi.org/10.1016/j.neucom.2022.07.066" @default.
- W4288045136 hasPublicationYear "2022" @default.
- W4288045136 type Work @default.
- W4288045136 citedByCount "2" @default.
- W4288045136 countsByYear W42880451362023 @default.
- W4288045136 crossrefType "journal-article" @default.
- W4288045136 hasAuthorship W4288045136A5048704738 @default.
- W4288045136 hasAuthorship W4288045136A5067483266 @default.
- W4288045136 hasAuthorship W4288045136A5071080919 @default.
- W4288045136 hasConcept C105795698 @default.
- W4288045136 hasConcept C11413529 @default.
- W4288045136 hasConcept C119247159 @default.
- W4288045136 hasConcept C119857082 @default.
- W4288045136 hasConcept C121332964 @default.
- W4288045136 hasConcept C124101348 @default.
- W4288045136 hasConcept C137250428 @default.
- W4288045136 hasConcept C147168706 @default.
- W4288045136 hasConcept C154945302 @default.
- W4288045136 hasConcept C163716315 @default.
- W4288045136 hasConcept C178650346 @default.
- W4288045136 hasConcept C185142706 @default.
- W4288045136 hasConcept C2776214188 @default.
- W4288045136 hasConcept C2778112365 @default.
- W4288045136 hasConcept C2780009758 @default.
- W4288045136 hasConcept C33923547 @default.
- W4288045136 hasConcept C41008148 @default.
- W4288045136 hasConcept C50644808 @default.
- W4288045136 hasConcept C54355233 @default.
- W4288045136 hasConcept C61326573 @default.
- W4288045136 hasConcept C62520636 @default.
- W4288045136 hasConcept C86803240 @default.
- W4288045136 hasConceptScore W4288045136C105795698 @default.
- W4288045136 hasConceptScore W4288045136C11413529 @default.
- W4288045136 hasConceptScore W4288045136C119247159 @default.
- W4288045136 hasConceptScore W4288045136C119857082 @default.
- W4288045136 hasConceptScore W4288045136C121332964 @default.
- W4288045136 hasConceptScore W4288045136C124101348 @default.
- W4288045136 hasConceptScore W4288045136C137250428 @default.
- W4288045136 hasConceptScore W4288045136C147168706 @default.
- W4288045136 hasConceptScore W4288045136C154945302 @default.
- W4288045136 hasConceptScore W4288045136C163716315 @default.
- W4288045136 hasConceptScore W4288045136C178650346 @default.
- W4288045136 hasConceptScore W4288045136C185142706 @default.
- W4288045136 hasConceptScore W4288045136C2776214188 @default.
- W4288045136 hasConceptScore W4288045136C2778112365 @default.
- W4288045136 hasConceptScore W4288045136C2780009758 @default.
- W4288045136 hasConceptScore W4288045136C33923547 @default.
- W4288045136 hasConceptScore W4288045136C41008148 @default.
- W4288045136 hasConceptScore W4288045136C50644808 @default.
- W4288045136 hasConceptScore W4288045136C54355233 @default.
- W4288045136 hasConceptScore W4288045136C61326573 @default.
- W4288045136 hasConceptScore W4288045136C62520636 @default.
- W4288045136 hasConceptScore W4288045136C86803240 @default.
- W4288045136 hasLocation W42880451361 @default.
- W4288045136 hasOpenAccess W4288045136 @default.
- W4288045136 hasPrimaryLocation W42880451361 @default.
- W4288045136 hasRelatedWork W143964308 @default.
- W4288045136 hasRelatedWork W2036224061 @default.
- W4288045136 hasRelatedWork W2060891144 @default.
- W4288045136 hasRelatedWork W2069407179 @default.
- W4288045136 hasRelatedWork W2141497691 @default.
- W4288045136 hasRelatedWork W2949256156 @default.
- W4288045136 hasRelatedWork W3080530454 @default.
- W4288045136 hasRelatedWork W4226291750 @default.
- W4288045136 hasRelatedWork W4286883315 @default.
- W4288045136 hasRelatedWork W4320341949 @default.
- W4288045136 hasVolume "509" @default.
- W4288045136 isParatext "false" @default.
- W4288045136 isRetracted "false" @default.
- W4288045136 workType "article" @default.