Learning Centre

Implementing Multi-Task Learning for Bayesian Optimization Structure Search

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.advisor Todorovic, Milica, Research Fellow, Aalto University, Department of Applied Physics, Finland
dc.contributor.advisor Remes, Ulpu, Postdoctoral Researcher, University of Helsinki, Department of Mathematics and Statistics, Finland
dc.contributor.author Sten, Nuutti Akilles
dc.date.accessioned 2020-05-20T09:00:05Z
dc.date.available 2020-05-20T09:00:05Z
dc.date.issued 2020
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/44208
dc.description.abstract Machine learning algorithms are highly dependent on the quality of the training data. Problems with the data, like accuracy and expenses in gathering it project directly to the cost and performance of the algorithm. Multi-task learning methods try to overcome this problem by combining information from multiple sources of data. In this study I focused on two existing methods for multi-output Gaussian processes, linear model of coregionalisation and intrinsic coregionalisation model. My aim in this study was to implement these algorithms to Bayesian Optimization Structure Search (BOSS) tool and test their potential for accelerating atomistic structure search space navigation with a simulation study. I found potential for reducing computational cost of optimization of expensive structure searches with multi-task learning. en
dc.format.extent 30 + app. 34
dc.format.mimetype application/pdf en
dc.language.iso en en
dc.publisher Aalto University en
dc.publisher Aalto-yliopisto fi
dc.subject.other Biotechnology en
dc.subject.other Computer science en
dc.subject.other Materials science en
dc.subject.other Mathematics en
dc.title Implementing Multi-Task Learning for Bayesian Optimization Structure Search en
dc.title Monilähteisen koneoppimisen soveltaminen Bayesilaiseen optimointiin aineen rakenteen laskennallisessa selvittämisessä fi
dc.type S harjoitus- ja seminaarityöt fi
dc.contributor.school Perustieteiden korkeakoulu fi
dc.contributor.school School of Science en
dc.contributor.department Teknillisen fysiikan laitos fi
dc.contributor.department Department of Applied Physics en
dc.subject.keyword Bayesian Optimization Structure Search en
dc.subject.keyword Gaussian Processes en
dc.subject.keyword Multi-task Learning en
dc.subject.keyword Coregionalization,Linear Model of Coregionalization en
dc.subject.keyword Electronic Structure Theory en
dc.subject.keyword Machine Learning for Materials Science en
dc.subject.keyword Transfer Learning en
dc.subject.keyword Aineen rakenne fi
dc.subject.keyword Bayesilainen optimointi fi
dc.subject.keyword Monilähteinen koneoppiminen fi
dc.subject.keyword Gaussin prosessi fi
dc.subject.keyword Siirtolähteinen koneoppiminen fi
dc.subject.keyword Laskennallinen materiaalitutkimus fi
dc.identifier.urn URN:NBN:fi:aalto-202005043002
dc.type.dcmitype text en
dc.programme.major Monimutkaiset Systeemit fi
dc.programme.major Complex Systems en
dc.programme.mcode SCI3060
dc.contributor.supervisor Rinke, Patrick, Associate Professor, Aalto University, Department of Applied Physics, Finland
dc.date.dateaccepted 2020-04-21
dc.contributor.lab Computational Electronic Structure Theory (CEST) en
dc.contributor.lab CEST-tutkimusryhmä fi
local.aalto.formfolder 2020_05_04_klo_11_09

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication