Theoretical and applicational advances in variational autoencoders

Resource type
Thesis type
(Thesis) Ph.D.
Date created
2019-12-02
Authors/Contributors
Author: He, Jiawei
Abstract
Variational autoencoders (VAEs) is a strong family of deep generative models based on variational inference (VI). Despite its recent success in modelling probabilistic data distributions, the original VAE framework make a strong assumption on the overly-simplified prior and approximate posterior, leading to limited modelling capacity. In this thesis, we propose novel solutions to alleviate this problem by introducing a learnable Bayesian network as the latent space of VAEs. In addition to the theoretical contributions to VAE research community, we also propose to apply VAEs to various promising applications including controllable video generation, asynchronous event sequences modelling and scene layout generation.
Document
Identifier
etd20678
Copyright statement
Copyright is held by the author.
Permissions
This thesis may be printed or downloaded for non-commercial research and scholarly purposes.
Scholarly level
Supervisor or Senior Supervisor
Thesis advisor: Mori, Greg
Member of collection
Attachment Size
etd20678.pdf 44.43 MB