College of Computing Theses and Dissertations
All materials in SMARTech are protected under U.S. Copyright Law and all rights are reserved. Such materials may be used, quoted or reproduced for educational purposes only with prior permission, provided proper attribution is given. Any redistribution, reproduction or use of the materials, in whole or in part, is prohibited without prior permission of the author.
Recent Submissions
-
Deep learning for building and validating geometric and semantic maps
(Georgia Institute of Technology, 2022-05-05)Mapping the world is an essential tool for making spatial artificial intelligence a reality in our near future. Spatial AI, or embodied intelligence for 3D perception, enables awareness and understanding of our surroundings. ... -
Enabling a Programming Environment for an Experimental Ion Trap Quantum Testbed
(Georgia Institute of Technology, 2022-05-03)Ion trap quantum hardware promises to provide a computational advantage over classical computing for specific problem spaces while also providing an alternative hardware implementation path to cryogenic quantum systems as ... -
CONTROLLABLE CONTENT BASED IMAGE SYNTHESIS AND IMAGE RETRIEVAL
(Georgia Institute of Technology, 2022-05-03)In this thesis, we address the problem of returning target images that match user queries in image retrieval and image synthesis. We investigate line drawing sketch as the main query, and explore several additional signals ... -
Semi-Parametric Continuous-Time Models for Adverse Health Behaviors
(Georgia Institute of Technology, 2022-05-13)Two important problems in behavioral medicine are modeling the risk of adverse health behaviors such as smoking, and classifying longitudinal health data to determine health conditions. Models for each can be used for ... -
OPTIMIZED SCHEDULING AND RESOURCE ALLOCATION FOR THREAD PARALLEL ARCHITECTURES
(Georgia Institute of Technology, 2022-05-03)Performance characteristics of irregular programs on parallel architectures were studied. Results indicated significant overheads of thread divergence and register utilization on the GPU and sub-optimal thread migrations ... -
Deep Multi-view Stereo for GTSFM
(Georgia Institute of Technology, 2022-05-03)Current structure-from-motion (SFM) pipelines integrated with multi-view stereo (MVS) module often applies traditional MVS algorithms. These algorithms cannot be well parallelized and can be slow when the data size and the ... -
Finding Dense Regions of Rapidly Changing Graphs
(Georgia Institute of Technology, 2022-05-02)Many of today's massive and rapidly changing graphs contain internal structure---hierarchies of locally dense regions---and finding and tracking this structure is key to detecting emerging behavior, exposing internal activity, ... -
Uncertainty Quantification in the context of 6D Pose Estimation
(Georgia Institute of Technology, 2022-05-03)We use the work on Deep Evidential Regression that was initially developed in the context of simple regression in R, and extend it to work on higher dimensional groups and manifolds with a Lie algebra structure. We develop ... -
New Directions in Garbled Circuits
(Georgia Institute of Technology, 2022-05-02)The Garbled Circuit (GC) technique is foundational in secure multiparty computation (MPC). GC allows parties to jointly and securely compute functions of their private inputs while revealing nothing but the output. GC is ... -
NEWS DATA VISUALIZATION INTERFACE DEVELOPMENT USING NMF ALGORITHM
(Georgia Institute of Technology, 2022-05-03)News data is a super large-scale dataset. It covers a wide range of topics ranging from heavy topics such as politics and society to beauty and entertainment, relatively light topics. At the same time, it is also the most ... -
Canonical Surface Mapping and Uncertainty Quantification in Deep Learning for 6D Pose Estimation
(Georgia Institute of Technology, 2022-05-03)In this work, we focus on the 6D pose estimation problem for single-view images. We divide our thesis into two main parts. For the first part, we work on solving the pose estimation problem by extending the ACSM neural ... -
Understanding, Fortifying and Democratizing AI Security
(Georgia Institute of Technology, 2022-04-19)As we steadily move towards an AI-powered utopia that could only be imagined in lofty fiction in the recent past, a formidable threat is emerging that endangers the acute capitalization of AI in our everyday lives. A growing ... -
Control plane for situation-awareness applications on geo-distributed resources
(Georgia Institute of Technology, 2022-05-03)Situation-awareness applications generate actionable knowledge from sensor and user data. Two trends are unlocking new situation-awareness applications: geo-distributed resources and pervasive sensors. Geo-distributed ... -
CATEGORY LEVEL POSE ESTIMATION VIA INSTANCE CANONICALIZATION
(Georgia Institute of Technology, 2022-01-14)This thesis describes a study of pose estimation. Pose estimation is the determination of an object’s position and orientation in some coordinate frame. Pose estimation has applica- tion in robotics, augmented/virtual ... -
Task Generalized MDPs for Multi-Task Reinforcement Learning
(Georgia Institute of Technology, 2022-01-14)Reinforcement learning (RL) has seen widespread success in creating intelligent agents in several challenging domains. Yet, training RL agents remains prohibitively expensive in terms of the number of environment interactions ... -
MITIGATING RACIAL BIASES IN TOXIC LANGUAGE DETECTION
(Georgia Institute of Technology, 2022-05-05)Recent research has demonstrated how racial biases against users who write African American English exists in popular toxic language datasets. While previous work has focused on a single fairness criteria, we propose to ... -
Improving Sparse Reward Classifiers for Model-Based Reinforcement Learning in Low-Data Regimes
(Georgia Institute of Technology, 2021-04-28)Model-Based Reinforcement Learning consists of learning a model of an environment in which we can train an agent. This approach is useful when we are limited in the number of interactions the agent can take with the ... -
Ubiquitous Self-Powered Ambient Light Sensing Surfaces
(Georgia Institute of Technology, 2021-05-01)Many human activities interfere with ambient light in a predictable and detectable way in that our activities implicitly or explicitly block the paths of ambient light in our environment. This dissertation explores sensing ... -
Data Privacy in the Modern Machine Learning Ecosystem
(Georgia Institute of Technology, 2021-04-30)The explosion of data collection and advances in artificial intelligence and machine learning have motivated a robust economy around cloud-based machine learning services. While such services provide opportunities for a ... -
Nuclear Communities: Epistemic Community Structure and Nuclear Proliferation Latency
(Georgia Institute of Technology, 2021-05-03)This dissertation examines variation in nuclear weapons proliferation outcomes and program duration. This seeks to address a persisting gap in the scholarship of nuclear weapons and their proliferation using quantitative ...