Files in this item

FilesDescriptionFormat

application/pdf

application/pdfYEH-DISSERTATION-2021.pdf (15MB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Extracting and learning structures from data
Author(s):Yeh, Raymond A
Director of Research:Schwing, Alexander G
Doctoral Committee Chair(s):Schwing, Alexander G
Doctoral Committee Member(s):Hasegawa-Johnson, Mark; Do, Minh N; Forsyth, David
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:Ph.D.
Genre:Dissertation
Subject(s):machine learning
computer vision
Abstract:In this work, we study models which explicitly capture and learn structures from data. For the task of supervised and unsupervised textual grounding, we propose a unified framework which links words to image concepts. A parameter between each word and image concept is learned and the learned parameters are easily interpretable. Next, for the task of generative modeling of multi-agent trajectories, we design models which share parameters based on the relationship between agents in the system to achieve permutation equivariance. This representation is particularly suitable in a multi-agent setting where the identity of the agents is unknown. We achieve better performance than conventional fully connected deep nets. Lastly, we present a framework on how to learn equivariance properties from data; this framework is based on learning how to share parameters in a model. We provide analysis on Gaussian vectors in terms on mean squared error criterion and empirically show that our approach can recover shift and permutation equivariances.
Issue Date:2021-04-21
Type:Thesis
URI:http://hdl.handle.net/2142/110702
Rights Information:Copyright 2021 Raymond Yeh
Date Available in IDEALS:2021-09-17
Date Deposited:2021-05


This item appears in the following Collection(s)

Item Statistics