Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/231424
Title: DEEP GENERATIVE MODELING FOR IMAGES AND TIME SERIES
Authors: ABDUL FATIR ANSARI
ORCID iD:   orcid.org/0000-0003-0263-9142
Keywords: Generative Models, Generative Adversarial Networks, Variational Inference, Gradient Flows, State Space Models, Machine Learning
Issue Date: 23-Jan-2022
Citation: ABDUL FATIR ANSARI (2022-01-23). DEEP GENERATIVE MODELING FOR IMAGES AND TIME SERIES. ScholarBank@NUS Repository.
Abstract: Deep generative models (DGMs) have excelled at modeling high-dimensional data. In this thesis, we propose new DGMs and methods, focusing on image and time series data, that seek to address the research challenges associated with DGMs. We begin with DGMs for images, offering a fresh perspective on the problem of learning in generative adversarial networks (GANs) by formulating it as minimizing the distance between characteristic functions. Further, since sample quality is generally inconsistent for any given generative model, we introduce a technique that refines samples using the gradient flow of f-divergences. In the second part, we focus on DGMs for time series. We propose a flexible state space model parameterized by neural networks that is capable of identifying both state- and time-dependent switching dynamics in time series data. State-dependent switching is enabled by a recurrent state-to-switch connection and explicit duration count variables are used to improve the time-dependent switching behavior.
URI: https://scholarbank.nus.edu.sg/handle/10635/231424
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
AnsariAF.pdf19.38 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

63
checked on Nov 17, 2022

Download(s)

8
checked on Nov 17, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.