article · Keisan Rikigaku Koenkai koen ronbunshu/Keisan Rikigaku Kouenkai kouen rombunshuu · 2022

The Construction and Applications of Bayesian Variational Integrator Networks

Cited by 0Open access

Abstract

In numerical analysis, the conservation of structure, i.e., whether the essential properties of physical phenomena can be reproduced numerically, is of great importance. On the other hand, neural networks that can learn conservation laws has recently received great attention. These models take important structure of physical problems into consideration, which are often ignored in traditional models that directly learn using data, consequently exhibiting long-term accurate prediction and interpretability. In the current study, we construct neural network models based on variational integrator, a typical kind of structure-preserving method. In addition, we introduce Bayesian framework to measure uncertainty of the model and evaluate the models quantitively. Illustrative examples are studied.

Cite this paper

APA 7

OTAKE, M., & Peng, L. (2022). The Construction and Applications of Bayesian Variational Integrator Networks. Keisan Rikigaku Koenkai koen ronbunshu/Keisan Rikigaku Kouenkai kouen rombunshuu, 2022.35(0), 13–01. https://doi.org/10.1299/jsmecmd.2022.35.13-01

MLA 9

OTAKE, Momoko, and Linyu Peng. “The Construction and Applications of Bayesian Variational Integrator Networks.” Keisan Rikigaku Koenkai koen ronbunshu/Keisan Rikigaku Kouenkai kouen rombunshuu, vol. 2022.35, no. 0, 2022, pp. 13–01, https://doi.org/10.1299/jsmecmd.2022.35.13-01.

Chicago

OTAKE, Momoko, and Linyu Peng. 2022. “The Construction and Applications of Bayesian Variational Integrator Networks.” Keisan Rikigaku Koenkai koen ronbunshu/Keisan Rikigaku Kouenkai kouen rombunshuu 2022.35 (0): 13–01. https://doi.org/10.1299/jsmecmd.2022.35.13-01.

Harvard

OTAKE, M. and Peng, L. (2022) ‘The Construction and Applications of Bayesian Variational Integrator Networks’, Keisan Rikigaku Koenkai koen ronbunshu/Keisan Rikigaku Kouenkai kouen rombunshuu, 2022.35(0), pp. 13–01. Available at: https://doi.org/10.1299/jsmecmd.2022.35.13-01.

BibTeX

@article{otake2022construction,
  title = {{The Construction and Applications of Bayesian Variational Integrator Networks}},
  author = {OTAKE, Momoko and Peng, Linyu},
  journal = {Keisan Rikigaku Koenkai koen ronbunshu/Keisan Rikigaku Kouenkai kouen rombunshuu},
  volume = {2022.35},
  number = {0},
  pages = {13--01},
  year = {2022},
  doi = {10.1299/jsmecmd.2022.35.13-01}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.