Show simple item record

dc.rights.licenseCC-BY-NC-ND
dc.contributor.advisorMosk, A.P.
dc.contributor.advisorvan Oosten, D.
dc.contributor.authorHuitink, S.M.
dc.date.accessioned2019-08-20T17:00:39Z
dc.date.available2019-08-20T17:00:39Z
dc.date.issued2019
dc.identifier.urihttps://studenttheses.uu.nl/handle/20.500.12932/33463
dc.description.abstractTo this day machine learning has been executed by computers. In this thesis, we research the possibility, and difficulties, of an experiment that performs machine learning tasks using light propagation. This would be more energy-efficient as well as faster than current machines. We study the effect that noise, which is unavoidable in the real setup, will have on the experiment. We find that small quantities of noise during training can decrease the validation accuracy of a model with a few percents. For a model that is trained without noise, the validation effciency is not affected strongly by noise.
dc.description.sponsorshipUtrecht University
dc.format.extent1322583
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.titleThe effect of noise on an optical machine learning model
dc.type.contentBachelor Thesis
dc.rights.accessrightsOpen Access
dc.subject.keywordsOptics, Machine learning, Deep learning, MNIST
dc.subject.courseuuNatuur- en Sterrenkunde


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record