Back to search

University of Washington

Understanding Variational Autoencoders and Disentanglement Metrics

Abstract

dc:description.abstract

In this thesis, we conduct a thorough study of "Variational Autoencoders". We explain the limitations of ``supervised learning" and emphasize the need for ``generative models" to solve complex problems. Variational Autoencoder (VAE) is an effective tool for generative modeling. We understand the rich mathematical basis of VAEs, the evidence lower bound (ELBO) and how regularization of original VAEs brings the trade-off between reconstruction fidelity and quality of disentanglement within the learnt representations. We validate the theory by conducting experiments on Frey's Faces image dataset using an encoder and decoder architecture using convolutional neural networks . In addition to this, we also learn what constitutes a ``good representation" and how "disentanglement metrics" helps in comparing representations obtained from two different models. We briefly describe two different types of disentanglement metrics Beta-VAE metric and Mutual Information Gap (MIG).

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Hassan Ananda Kumar, Kruthika
Advisor dc:contributor.advisor
  • Kutz, Nathan J

Subjects

dc:subject × 8

Rights

dc:rights
Statement dc:rights
  • none
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1773/48435

Chain of custody

source
Harvested from
University of Washington
Base URL
digital.lib.washington.edu/server/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Hassan Ananda Kumar, Kruthika. Understanding Variational Autoencoders and Disentanglement Metrics. 2022. http://hdl.handle.net/1773/48435