Deep Form Finding Using Variational Autoencoders for deep form finding of structural typologies

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorde Miguel, Jaimeen_US
dc.contributor.authorEugenia Villafane, Mariaen_US
dc.contributor.authorPiskorec, Lukaen_US
dc.contributor.authorSancho-Caparrini, Fernandoen_US
dc.contributor.departmentDepartment of Architectureen
dc.contributor.editorSousa, JPen_US
dc.contributor.editorHenriques, GCen_US
dc.contributor.editorXavier, JPen_US
dc.contributor.organizationUniversity of Sevilleen_US
dc.contributor.organizationUniversity College Londonen_US
dc.date.accessioned2020-09-18T06:47:02Z
dc.date.available2020-09-18T06:47:02Z
dc.date.issued2019en_US
dc.description.abstractIn this paper, we are aiming to present a methodology for generation, manipulation and form finding of structural typologies using variational autoencoders, a machine learning model based on neural networks. We are giving a detailed description of the neural network architecture used as well as the data representation based on the concept of a 3D-canvas with voxelized wireframes. In this 3D-canvas, the input geometry of the building typologies is represented through their connectivity map and subsequently augmented to increase the size of the training set. Our variational autoencoder model then learns a continuous latent distribution of the input data from which we can sample to generate new geometry instances, essentially hybrids of the initial input geometries. Finally, we present the results of these computational experiments and lay out the conclusions as well as outlook for future research in this field.en
dc.description.versionPeer revieweden
dc.format.extent10
dc.format.extent71-80
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationde Miguel, J, Eugenia Villafane, M, Piskorec, L & Sancho-Caparrini, F 2019, Deep Form Finding Using Variational Autoencoders for deep form finding of structural typologies . in JP Sousa, GC Henriques & JP Xavier (eds), ECAADE SIGRADI 2019: ARCHITECTURE IN THE AGE OF THE 4TH INDUSTRIAL REVOLUTION, VOL 1 . vol. 1, eCAADe proceedings, eCAADe, pp. 71-80, 37th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe) & 23rd Conference of the Iberoamerican Society Digital Graphics (SIGraDi), Porto, Portugal, 11/09/2019 . < http://papers.cumincad.org/data/works/att/ecaadesigradi2019_514.pdf >en
dc.identifier.isbn978-94-91207-17-4
dc.identifier.issn2684-1843
dc.identifier.otherPURE UUID: a8c3c7f8-cc58-4b8d-bbee-7aafd896e02ben_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/a8c3c7f8-cc58-4b8d-bbee-7aafd896e02ben_US
dc.identifier.otherPURE LINK: http://papers.cumincad.org/data/works/att/ecaadesigradi2019_514.pdfen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/51397091/ecaadesigradi2019_514.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/46516
dc.identifier.urnURN:NBN:fi:aalto-202009185452
dc.language.isoenen
dc.relation.ispartof37th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe) & 23rd Conference of the Iberoamerican Society Digital Graphics (SIGraDi)en
dc.relation.ispartofseriesECAADE SIGRADI 2019: ARCHITECTURE IN THE AGE OF THE 4TH INDUSTRIAL REVOLUTION, VOL 1en
dc.relation.ispartofseriesVolume 1en
dc.relation.ispartofserieseCAADe proceedingsen
dc.rightsopenAccessen
dc.subject.keywordartificial intelligenceen_US
dc.subject.keyworddeep neural networksen_US
dc.subject.keywordvariational autoencodersen_US
dc.subject.keywordgenerative designen_US
dc.subject.keywordform findingen_US
dc.subject.keywordstructural designen_US
dc.titleDeep Form Finding Using Variational Autoencoders for deep form finding of structural typologiesen
dc.typeA4 Artikkeli konferenssijulkaisussafi
dc.type.versionpublishedVersion
Files
Collections
[article-cris] Taiteiden ja suunnittelun korkeakoulu / ARTS