Recent Submissions

  • Scalable Data Mining via Constrained Low Rank Approximation 

    Eswar, Srinivas (Georgia Institute of Technology, 2022-08-01)
    Matrix and tensor approximation methods are recognised as foundational tools for modern data analytics. Their strength lies in their long history of rigorous and principled theoretical foundations, judicious formulations ...
  • Robust Efficient Edge AI: New Principles and Frameworks for Empowering Artificial Intelligence on Edge Devices 

    Duggal, Rahul (Georgia Institute of Technology, 2022-08-02)
    Deep learning has revolutionised a breadth of industries by automating critical tasks while achieving superhuman accuracy. However, many of these benefits are driven by huge neural networks deployed on cloud servers that ...
  • A Scalable Edge-Centric System Design for Camera Networks to aid Situation Awareness Applications 

    Xu, Zhuangdi (Georgia Institute of Technology, 2022-08-01)
    The ubiquity of cameras in our environment coupled with advances in computer vision and machine learning has enabled several novel applications combining sensing, processing, and actuation. Often referred to as situation ...
  • Deterrence through Entanglement 

    Stewart, Brian (Georgia Institute of Technology, 2022-07-30)
    Many components of the Nuclear Command, Control, and Communications (NC3) architecture of the United States are vulnerable space systems. These space systems are considered entangled, which means they support both strategic ...
  • Robust Reservoir Computing Approaches for Predicting Cardiac Electrical Dynamics 

    Shahi, Shahrokh (Georgia Institute of Technology, 2022-07-29)
    Computational modeling of cardiac electrophysiological signaling is of vital importance in understanding, preventing, and treating life-threatening arrhythmias. Traditionally, mathematical models incorporating physical ...
  • Language Guided Localization and Navigation 

    Hahn, Meera (Georgia Institute of Technology, 2022-07-26)
    Embodied tasks that require active perception are key to improving language grounding models and creating holistic social agents. In this dissertation we explore four multi-modal embodied perception tasks and which require ...
  • Efficient methods for read mapping 

    Zhang, Haowen (Georgia Institute of Technology, 2022-08-01)
    DNA sequencing is the mainstay of biological and medical research. Modern sequencing machines can read millions of DNA fragments, sampling the underlying genomes at high-throughput. Mapping the resulting reads to a reference ...
  • Deep generative models for solving geophysical inverse problems 

    Siahkoohi, Ali (Georgia Institute of Technology, 2022-07-19)
    My thesis presents several novel methods to facilitate solving large-scale inverse problems by utilizing recent advances in machine learning, and particularly deep generative modeling. Inverse problems involve reliably ...
  • Towards Realistic Embodied AI Agents 

    Datta, Samyak (Georgia Institute of Technology, 2022-07-28)
    Recent years have witnessed the inception of a growing field of inquiry within the broader AI community termed as "Embodied AI". Problems studied under the umbrella of Embodied AI include the introduction of scene datasets ...
  • Designing human-centered technologies to mobilize social media data into institutional contexts 

    Alvarado Garcia, Adriana (Georgia Institute of Technology, 2022-07-12)
    Social media platforms have become an established and alternative mechanism for communities to mobilize and exchange information in response to humanitarian or local crises. Due to the richness of experiences accumulated ...
  • Emergence of Intelligent Navigation Behavior in Embodied Agents from Massive-Scale Simulation 

    Wijmans, Erik (Georgia Institute of Technology, 2022-08-01)
    The goal of Artificial Intelligence is to build ‘thinking machines’ that ‘use language, form abstractions and concepts, solve kinds of problems now reserved for humans, and improve themselves.’ In this dissertation, we ...
  • High-Performance Software for Quantum Chemistry and Hierarchical Matrices 

    Erlandson, Lucas Alden (Georgia Institute of Technology, 2022-05-20)
    Linear algebra is the underpinning of a significant portion of the computation done in the modern age. Applications relying on linear algebra include physical and chemical simulations, machine learning, artificial intelligence, ...
  • DEEP LEARNING METHODS FOR MULTI-MODAL HEALTHCARE DATA 

    Biswal, Siddharth (Georgia Institute of Technology, 2022-05-19)
    Abstract: Today, enormous transformations are happening in health care research and applications. In the past few years, there has been exponential growth in the amount of healthcare data generated from multiple sources. ...
  • Interpreting Neural Networks for and with Natural Language 

    Wiegreffe, Sarah Augusta (Georgia Institute of Technology, 2022-05-18)
    In the past decade, natural language processing (NLP) systems have come to be built almost exclusively on a backbone of large neural models. As the landscape of feasible tasks has widened due to the capabilities of these ...
  • Hardware-Assisted Processor Tracing for Automated Bug Finding and Exploit Prevention 

    Yagemann, Carter (Georgia Institute of Technology, 2022-05-10)
    The proliferation of binary-only program analysis techniques like fuzz testing and symbolic analysis have lead to an acceleration in the number of publicly disclosed vulnerabilities. Unfortunately, while bug finding has ...
  • Analysis and Maintenance of Graph Laplacians via Random Walks 

    Gao, Yu (Georgia Institute of Technology, 2022-05-16)
    Graph Laplacians arise in many natural and artificial contexts. They are linear systems associated with undirected graphs. They are equivalent to electric flows which is a fundamental physical concept by itself and is ...
  • MODELING THE LEADERSHIP OF LANGUAGE CHANGE FROM DIACHRONIC TEXT 

    Soni, Sandeep Brijlal (Georgia Institute of Technology, 2021-07-21)
    Natural languages constantly change over time. These changes are modulated by social factors such as influence which are not always directly observable. However, large-scale computational modeling of language change using ...
  • Integrating Distributional, Compositional, and Relational Approaches to Neural Word Representations 

    Pinter, Yuval D. (Georgia Institute of Technology, 2021-06-17)
    When the field of natural language processing (NLP) entered the era of deep neural networks, the task of representing basic units of language, an inherently sparse and symbolic medium, using low-dimensional dense real-valued ...
  • Coordinating Team Tactics for Swarm-vs.-Swarm Adversarial Games 

    Strickland, Laura Gail (Georgia Institute of Technology, 2022-07-12)
    While swarms of UAVs have received much attention in the last few years, adversarial swarms (i.e., competitive, swarm-vs.-swarm games) have been less well studied. In this dissertation, I investigate the factors influential ...
  • Deep learning for building and validating geometric and semantic maps 

    Lambert, John (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. ...

View more