Recurrent neural network-induced Gaussian process
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Sun X. | - |
dc.contributor.author | Kim, Seongyoon | - |
dc.contributor.author | Choi J.-I. | - |
dc.date.accessioned | 2023-04-10T06:40:04Z | - |
dc.date.available | 2023-04-10T06:40:04Z | - |
dc.date.issued | 2022-10 | - |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.uri | https://yscholarhub.yonsei.ac.kr/handle/2021.sw.yonsei/6392 | - |
dc.description.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. | - |
dc.format.extent | 10 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | ELSEVIER | - |
dc.title | Recurrent neural network-induced Gaussian process | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1016/j.neucom.2022.07.066 | - |
dc.identifier.scopusid | 2-s2.0-85136589254 | - |
dc.identifier.bibliographicCitation | NEUROCOMPUTING, v.509, pp 75 - 84 | - |
dc.citation.title | NEUROCOMPUTING | - |
dc.citation.volume | 509 | - |
dc.citation.startPage | 75 | - |
dc.citation.endPage | 84 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in Scholar Hub are protected by copyright, with all rights reserved, unless otherwise indicated.
Yonsei University 50 Yonsei-ro Seodaemun-gu, Seoul, 03722, Republic of Korea1599-1885
© 2021 YONSEI UNIV. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.