Discovering invariants via machine learning

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 216
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorHa, Seungwoongko
dc.contributor.authorJeong, Hawoongko
dc.date.accessioned2022-01-04T06:40:43Z-
dc.date.available2022-01-04T06:40:43Z-
dc.date.created2022-01-04-
dc.date.created2022-01-04-
dc.date.created2022-01-04-
dc.date.created2022-01-04-
dc.date.issued2021-12-
dc.identifier.citationPHYSICAL REVIEW RESEARCH, v.3, no..4-
dc.identifier.issn2643-1564-
dc.identifier.urihttp://hdl.handle.net/10203/291475-
dc.description.abstractInvariants and conservation laws convey critical information about the underlying dynamics of a system, yet it is generally infeasible to find them from large-scale data without any prior knowledge or human insight. We propose ConservNet to achieve this goal, a neural network that spontaneously discovers a conserved quantity from grouped data where the members of each group share invariants, similar to a general experimental setting where trajectories from different trials are observed. As a neural network trained with an intuitive loss function called noise-variance loss, ConservNet learns the hidden invariants in each group of multidimensional observables in a data-driven end-to-end manner. Our model successfully discovers underlying invariants from the simulated systems having invariants as well as a real-world double-pendulum trajectory. Since the model is robust to various noises and data conditions compared to the baseline, our approach is directly applicable to experimental data for discovering hidden conservation laws and further, general relationships between variables.-
dc.languageEnglish-
dc.publisherAMER PHYSICAL SOC-
dc.titleDiscovering invariants via machine learning-
dc.typeArticle-
dc.identifier.scopusid2-s2.0-85122558616-
dc.type.rimsART-
dc.citation.volume3-
dc.citation.issue.4-
dc.citation.publicationnamePHYSICAL REVIEW RESEARCH-
dc.identifier.doi10.1103/PhysRevResearch.3.L042035-
dc.contributor.localauthorJeong, Hawoong-
dc.description.isOpenAccessY-
dc.type.journalArticleArticle-
dc.subject.keywordPlusLAWS-
Appears in Collection
PH-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0