Skip to main content

Structured Disentangling Networks for Learning Deformation Invariant Latent Spaces

Abstract Disentangling latent spaces is an important research direction in the interpretability of unsupervised machine learning. Several recent works using deep learning are very effective at producing disentangled representations. However, in the unsupervised setting, there is no way to pre-specify which part of the latent space captures specific factors of variations. While this is generally a hard problem because of the non-existence of analytical expressions to capture these variations, there are certain factors like geometric

transforms that can be expressed analytically. Furthermore, in existing frameworks, the disentangled values are also not interpretable. The focus of this work is to disentangle these geometric factors of variation... (more)
Created Date 2019
Contributor Koneripalli, Kaushik (Author) / Turaga, Pavan (Advisor) / Papandreou-Suppappola, Antonia (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Subject Electrical engineering / Computer science / Affine transforms / Autoencoders / Disentanglement / Invariance / Latent spaces
Type Masters Thesis
Extent 53 pages
Language English
Note Masters Thesis Electrical Engineering 2019
Collaborating Institutions Graduate College / ASU Library
Additional Formats MODS / OAI Dublin Core / RIS

  Full Text
5.3 MB application/pdf
Download Count: 1

Description Dissertation/Thesis