Gauge equivariant convolutional neural networks

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/301431
Download file(s):
File Description SizeFormat 
Master_Thesis_Oscar_Carlsson.pdf1.26 MBAdobe PDFView/Open
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCarlsson, Oscar-
dc.contributor.departmentChalmers tekniska högskola / Institutionen för fysiksv
dc.date.accessioned2020-08-04T12:39:54Z-
dc.date.available2020-08-04T12:39:54Z-
dc.date.issued2020sv
dc.date.submitted2020-
dc.identifier.urihttps://hdl.handle.net/20.500.12380/301431-
dc.description.abstractIn this thesis we present a review of the current theory of group and gauge equivariant convolutional neural networks on homogeneous spaces and general smooth manifolds, with focus on the latter, formulated from a mathematical viewpoint. We also provide a new interpretation of layers in neural networks as maps between associated bundles. Furthermore we discuss the implementation of simple convolutional neural networks invariant under 90 rotations and reflections, build such networks, and test them to show the effect of the invariant construction. This testing shows that the addition of the group invariant structure allows the network to efficiently classify transformed data while only training on untransformed data.sv
dc.language.isoengsv
dc.setspec.uppsokPhysicsChemistryMaths-
dc.subjectConvolutional neural networkssv
dc.subjectmachine learningsv
dc.subjectmanifoldssv
dc.subjectgroupsv
dc.subjectgaugesv
dc.subjectPythonsv
dc.subjectTensorflowsv
dc.subjectKerassv
dc.titleGauge equivariant convolutional neural networkssv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH-
dc.contributor.examinerBerman, Robert-
dc.contributor.supervisorPersson, Daniel-
dc.identifier.coursecodeTIFX05sv
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.