Invertible Neural Network utilizing Glow
Keywords
No Thumbnail Available
Authors
Issue Date
2020-07-01
Language
en
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Normalizing flows are rising in popularity, but a disadvantage is that information
is often lost during the transformation between distributions. This problem is tackled by introducing the concept of marginalizing flows, which are added on top of a normalizing flow. They add a variable epsilon to the data, which contains thrown-away data, before being passed through the normalizing flow. Marginalizing over epsilon then should contain more information than only using a normalizing flow, which is what is tested here. The specific normalizing flow used is Glow, with a marginalizing flow that applies a padding of 4 to the right and bottom borders. Results indicate that the improvement in performance that marginalizing flows offer is insignificant.
Description
Citation
Supervisor
Faculty
Faculteit der Sociale Wetenschappen