Implementing Multi-Task Learning for Bayesian Optimization Structure Search

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.advisorTodorovic, Milica, Research Fellow, Aalto University, Department of Applied Physics, Finland
dc.contributor.advisorRemes, Ulpu, Postdoctoral Researcher, University of Helsinki, Department of Mathematics and Statistics, Finland
dc.contributor.authorSten, Nuutti Akilles
dc.contributor.departmentTeknillisen fysiikan laitosfi
dc.contributor.departmentDepartment of Applied Physicsen
dc.contributor.labComputational Electronic Structure Theory (CEST)en
dc.contributor.labCEST-tutkimusryhmäfi
dc.contributor.schoolPerustieteiden korkeakoulufi
dc.contributor.schoolSchool of Scienceen
dc.contributor.supervisorRinke, Patrick, Associate Professor, Aalto University, Department of Applied Physics, Finland
dc.date.accessioned2020-05-20T09:00:05Z
dc.date.available2020-05-20T09:00:05Z
dc.date.dateaccepted2020-04-21
dc.date.issued2020
dc.description.abstractMachine 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.extent30 + app. 34
dc.format.mimetypeapplication/pdfen
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/44208
dc.identifier.urnURN:NBN:fi:aalto-202005043002
dc.language.isoenen
dc.programme.majorMonimutkaiset Systeemitfi
dc.programme.majorComplex Systemsen
dc.programme.mcodeSCI3060
dc.publisherAalto Universityen
dc.publisherAalto-yliopistofi
dc.subject.keywordBayesian Optimization Structure Searchen
dc.subject.keywordGaussian Processesen
dc.subject.keywordMulti-task Learningen
dc.subject.keywordCoregionalization,Linear Model of Coregionalizationen
dc.subject.keywordElectronic Structure Theoryen
dc.subject.keywordMachine Learning for Materials Scienceen
dc.subject.keywordTransfer Learningen
dc.subject.keywordAineen rakennefi
dc.subject.keywordBayesilainen optimointifi
dc.subject.keywordMonilähteinen koneoppiminenfi
dc.subject.keywordGaussin prosessifi
dc.subject.keywordSiirtolähteinen koneoppiminenfi
dc.subject.keywordLaskennallinen materiaalitutkimusfi
dc.subject.otherBiotechnologyen
dc.subject.otherComputer scienceen
dc.subject.otherMaterials scienceen
dc.subject.otherMathematicsen
dc.titleImplementing Multi-Task Learning for Bayesian Optimization Structure Searchen
dc.titleMonilähteisen koneoppimisen soveltaminen Bayesilaiseen optimointiin aineen rakenteen laskennallisessa selvittämisessäfi
dc.typeS harjoitus- ja seminaarityötfi
dc.type.dcmitypetexten
local.aalto.formfolder2020_05_04_klo_11_09
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
sem_sten_nuutti akilles_2020.pdf
Size:
2.32 MB
Format:
Adobe Portable Document Format
Download
Collections
[sem] Perustieteiden korkeakoulu / SCI