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
-
Neurosymbolic automated story generation
(Georgia Institute of Technology, 2021-04-07)Although we are currently riding a technological wave of personal assistants, many of these agents still struggle to communicate appropriately. Humans are natural storytellers, so it would be fitting if artificial intelligence ... -
Optimizing resource allocation in computational sustainability: Models, algorithms and tools
(Georgia Institute of Technology, 2021-01-21)The 17 Sustainable Development Goals laid out by the United Nations include numerous targets as well as indicators of progress towards sustainable development. Decision-makers tasked with meeting these targets must frequently ... -
Empowering users to communicate their preferences to machine learning models in Visual Analytics
(Georgia Institute of Technology, 2021-01-21)Recent visual analytic (VA) systems rely on machine learning (ML) to allow users to perform a variety of data analytic tasks, e.g., biologists clustering genome samples, medical practitioners predicting the diagnosis for ... -
Compiler analysis and optimization of memory management In modern processors
(Georgia Institute of Technology, 2021-01-19)Modern processors, such as CPUs and GPUs have continued to deliver higher performance with increasing microarchitecture innovations in recent years. However, it is non-trivial for application developers to achieve anywhere ... -
On Using Inductive Biases for Designing Deep Learning Architectures
(Georgia Institute of Technology, 2020-12-15)Recent advancements in field of Artificial Intelligence, especially in the field of Deep Learning (DL), have paved way for new and improved solutions to complex problems occurring in almost all domains. Often we have some ... -
Towards Transparent and Grounded Visual AI Systems
(Georgia Institute of Technology, 2020-04-27)My research goal is to build transparent and grounded AI systems. More specifically, my research tries to answer the question -- Do deep visual models make their decisions for the "right reasons"? In my dissertation, I ... -
A Flash Tier For Tiered Transaction Storage System
(Georgia Institute of Technology, 2020-04-23)A tiered transaction storage subsystem (T2) providing both ease of programming and cost effectiveness is proposed. The dissertation explores the system aspects of a tiered storage system consisting of memory and flash tiers ... -
Computational Methods for Measurement of Visual Attention from Videos towards Large-Scale Behavioral Analysis
(Georgia Institute of Technology, 2020-02-18)Visual attention is one of the most important aspects of human social behavior, visual navigation, and interaction with the world, revealing information about their social, cognitive, and affective states. Although ... -
Performance Primitives for Artificial Neural Networks
(Georgia Institute of Technology, 2021-05-10)Optimized software implementations of artificial neural networks leverage primitives from performance libraries, such as the BLAS. However, these primitives were prototyped decades ago, and do not necessarily reflect the ... -
Interval Deep Learning for Uncertainty Quantification in Engineering Problems
(Georgia Institute of Technology, 2021-05-06)Deep neural networks are becoming more common in important real-world safety-critical applications where reliability in the predictions is paramount. Despite their exceptional prediction capabilities, current deep neural ... -
Performant Software Hardening under Hardware Support
(Georgia Institute of Technology, 2021-05-06)With a booming number of applications and end-users in the past decade, software security has been emphasized more than ever. Nonetheless, a consistent increase of security-critical bugs has been observed along the way, ... -
Overcoming Memory Capacity Constraints for Large Graph Applications on GPUs
(Georgia Institute of Technology, 2021-05-01)Graphics Processing Units (GPUs) have been used successfully for accelerating a wide variety of applications in the domains of scientific computing, machine learning, and data analytics over the last decade. Two important ... -
An IR-based Fuzzing Approach for Finding Context-Aware Bugs in API-based systems
(Georgia Institute of Technology, 2021-05-03)API-based systems, a large group of security-critical software programs including web browser and OS kernels, accept program inputs being composed of API calls. Considering the scale and complexity of an API-based system, ... -
REDUCING SOFTWARE’S ATTACK SURFACE WITH CODE DEBLOATING
(Georgia Institute of Technology, 2021-05-01)Current software is designed to support a large spectrum of features to meet various users’ needs. However, each end-user only requires a small set of the features to perform required tasks, rendering the software bloated. ... -
FROM NEEDS TO STRENGTHS: DEVISING ASSETS-BASED PARENT-EDUCATION ICTS FOR LATINX/A/O IMMIGRANT PARENTS IN THE UNITED STATES
(Georgia Institute of Technology, 2021-04-28)Immigration to higher-income countries such as the United States (U.S.) is a worldwide, growing phenomenon. As the number of people moving across the world increases, so does the number of children of immigrants needing ... -
EMBODIMENT IN COMPUTER SCIENCE LEARNING: HOW SPACE, METAPHOR, GESTURE, AND SKETCHING SUPPORT STUDENT LEARNING
(Georgia Institute of Technology, 2021-05-01)Recently, correlational studies have found that psychometrically assessed spatial skills may be influential in learning computer science (CS). Correlation does not necessarily mean causation; these correlations could be ... -
Scalable Energy-efficient Microarchitectures with Computational Error Tolerance
(Georgia Institute of Technology, 2021-04-28)Dennard scaling of conventional semiconductor technology has reached its limit resulting in issues pertaining to leakage current and threshold voltage. Energy-savings found at the transistor level by simply lowering supply ... -
Deploying Deep Neural Networks in Edge with Distribution
(Georgia Institute of Technology, 2021-05-01)The widespread applicability of deep neural networks (DNNs) has led edge computing to emerge as a trend to extend our capabilities to several domains such as robotics, autonomous technologies, and Internet-of-things devices. ... -
Data-Driven Approach using Machine Learning for Real-Time Flight Path Optimization
(Georgia Institute of Technology, 2021-04-27)Airlines typically gather all available weather information before departure to generate flight routes that avoid hazardous weather while minimizing operating expenditures. However, pilots potentially have to perform ... -
Facilitating Reliable Autonomy with Human-Robot Interaction
(Georgia Institute of Technology, 2021-04-29)Autonomous robots are increasingly deployed to complex environments in which we cannot predict all possible failure cases a priori. Robustness to failures can be provided by humans enacting the roles of: (1) developers who ...
RSS 1.0