Marginalizing Flows

Simple item page
dc.contributor.advisorAmbrogioni, L.
dc.contributor.authorde Boer, Stijn
dc.date.issued2020-07-30
dc.description.abstractWe introduce marginalizing ows, an extension to normalizing ows which allow for better density estimation by marginaliziation of auxiliary random variables. We give an outline of the shortcomings of normalizing ows and motivate our approach. We trained models with an architecture based on Real NVP by Dinh et al.[5] on several datasets. For low-dimensional data we see that marginalizing ows consistently predict higher likelihood than normalizing ows, but our results do not generalize to higher-dimensional data like images.en_US
dc.identifier.urihttps://theses.ubn.ru.nl/handle/123456789/12660
dc.language.isoenen_US
dc.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationBachelor Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.thesis.typeBacheloren_US
dc.titleMarginalizing Flowsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1003731Boer, de.pdf
Size:
2.63 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculteit der Sociale Wetenschappen