{"@context":{"@vocab":"https://cir.nii.ac.jp/schema/1.0/","rdfs":"http://www.w3.org/2000/01/rdf-schema#","dc":"http://purl.org/dc/elements/1.1/","dcterms":"http://purl.org/dc/terms/","foaf":"http://xmlns.com/foaf/0.1/","prism":"http://prismstandard.org/namespaces/basic/2.0/","cinii":"http://ci.nii.ac.jp/ns/1.0/","datacite":"https://schema.datacite.org/meta/kernel-4/","ndl":"http://ndl.go.jp/dcndl/terms/","jpcoar":"https://github.com/JPCOAR/schema/blob/master/2.0/"},"@id":"https://cir.nii.ac.jp/crid/1362825896181381760.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.1038/srep25890"}},{"identifier":{"@type":"URI","@value":"https://www.nature.com/articles/srep25890"}},{"identifier":{"@type":"URI","@value":"https://www.nature.com/articles/srep25890.pdf"}}],"dc:title":[{"@value":"Fast machine-learning online optimization of ultra-cold-atom experiments"}],"description":[{"type":"abstract","notation":[{"@value":"<jats:title>Abstract</jats:title><jats:p>We apply an online optimization process based on machine learning to the production of Bose-Einstein condensates (BEC). BEC is typically created with an exponential evaporation ramp that is optimal for ergodic dynamics with two-body s-wave interactions and no other loss rates, but likely sub-optimal for real experiments. Through repeated machine-controlled scientific experimentation and observations our ‘learner’ discovers an optimal evaporation ramp for BEC production. In contrast to previous work, our learner uses a Gaussian process to develop a statistical model of the relationship between the parameters it controls and the quality of the BEC produced. We demonstrate that the Gaussian process machine learner is able to discover a ramp that produces high quality BECs in 10 times fewer iterations than a previously used online optimization technique. Furthermore, we show the internal model developed can be used to determine which parameters are essential in BEC creation and which are unimportant, providing insight into the optimization process of the system.</jats:p>"}]}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1382825896181381773","@type":"Researcher","foaf:name":[{"@value":"P. B. Wigley"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381763","@type":"Researcher","foaf:name":[{"@value":"P. J. Everitt"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381772","@type":"Researcher","foaf:name":[{"@value":"A. van den Hengel"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381768","@type":"Researcher","foaf:name":[{"@value":"J. W. Bastian"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381770","@type":"Researcher","foaf:name":[{"@value":"M. A. Sooriyabandara"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381760","@type":"Researcher","foaf:name":[{"@value":"G. D. McDonald"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381769","@type":"Researcher","foaf:name":[{"@value":"K. S. Hardman"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381774","@type":"Researcher","foaf:name":[{"@value":"C. D. Quinlivan"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381771","@type":"Researcher","foaf:name":[{"@value":"P. Manju"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381762","@type":"Researcher","foaf:name":[{"@value":"C. C. N. Kuhn"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381766","@type":"Researcher","foaf:name":[{"@value":"I. R. Petersen"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381765","@type":"Researcher","foaf:name":[{"@value":"A. N. Luiten"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381767","@type":"Researcher","foaf:name":[{"@value":"J. J. Hope"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381764","@type":"Researcher","foaf:name":[{"@value":"N. P. Robins"}]},{"@id":"https://cir.nii.ac.jp/crid/1382825896181381761","@type":"Researcher","foaf:name":[{"@value":"M. R. Hush"}]}],"publication":{"publicationIdentifier":[{"@type":"EISSN","@value":"20452322"}],"prism:publicationName":[{"@value":"Scientific Reports"}],"dc:publisher":[{"@value":"Springer Science and Business Media LLC"}],"prism:publicationDate":"2016-05-16","prism:volume":"6","prism:number":"1","prism:startingPage":"25890"},"reviewed":"false","dc:rights":["https://creativecommons.org/licenses/by/4.0","https://creativecommons.org/licenses/by/4.0"],"url":[{"@id":"https://www.nature.com/articles/srep25890"},{"@id":"https://www.nature.com/articles/srep25890.pdf"}],"createdAt":"2016-05-16","modifiedAt":"2024-06-16","relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360004235059757312","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Designing Nanostructures for Phonon Transport via Bayesian Optimization"}]},{"@id":"https://cir.nii.ac.jp/crid/1360285708902850176","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Towards ultimate impedance of phonon transport by nanostructure interface"}]},{"@id":"https://cir.nii.ac.jp/crid/1360290617556618240","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Single-site-resolved imaging of ultracold atoms in a triangular optical lattice"}]},{"@id":"https://cir.nii.ac.jp/crid/1360290617671424768","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Designing thermal functional materials by coupling thermal transport calculations and machine learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360572092625415168","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Machine learning-based approach for automatically tuned feedback-controlled electromigration"}]},{"@id":"https://cir.nii.ac.jp/crid/1360580232143695872","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"A Generalized Framework of Multifidelity Max-Value Entropy Search Through Joint Entropy"}]},{"@id":"https://cir.nii.ac.jp/crid/1360580232156909440","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Machine learner optimization of optical nanofiber-based dipole traps"}]},{"@id":"https://cir.nii.ac.jp/crid/1360853567795747200","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Optical manipulation of the negative silicon-vacancy center in diamond"}]},{"@id":"https://cir.nii.ac.jp/crid/1390297824977894528","@type":"Article","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@language":"en","@value":"Pervasive Artificial Intelligence"}]},{"@id":"https://cir.nii.ac.jp/crid/1521136280032942080","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Creation and Manipulation of Quantized Vortices in Bose-Einstein Condensates Using Reinforcement Learning"}]}],"dataSourceIdentifier":[{"@type":"CROSSREF","@value":"10.1038/srep25890"},{"@type":"CROSSREF","@value":"10.1103/physrevx.7.021024_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"},{"@type":"CROSSREF","@value":"10.1063/1.5055570_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"},{"@type":"CROSSREF","@value":"10.1088/1367-2630/abcdc8_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"},{"@type":"CROSSREF","@value":"10.1063/5.0017042_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"},{"@type":"CROSSREF","@value":"10.7566/jpsj.89.074006_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"},{"@type":"CROSSREF","@value":"10.1063/1.5143051_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"},{"@type":"CROSSREF","@value":"10.1162/neco_a_01530_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"},{"@type":"CROSSREF","@value":"10.1116/5.0086507_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"},{"@type":"CROSSREF","@value":"10.1103/physreva.102.022616_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"},{"@type":"CROSSREF","@value":"10.53829/ntr201710fa6_references_DOI_ExPrZ1E4uGyRQsBADAIr12ngDE4"}]}