The College of Computing has built a reputation for providing challenging courses and an overall rewarding academic experience at all levels. In the undergraduate program, the College awards bachelor's degrees in computer science, and in the graduate program, the College offers master's and doctoral degrees in computer science. The College offers an undergraduate certificate in Information Systems jointly with the DuPree College of Management and an undergraduate minor and undergraduate and graduate certificates in Cognitive Science jointly with the Schools of Psychology and Industrial and Systems Engineering.

Sub-communities within this community

Collections in this community

Recent Submissions

  • Improved search techniques for structured prediction 

    Vijayakumar, Ashwin Kalyan (Georgia Institute of Technology, 2020-07-29)
    Many useful AI tasks like machine translation, captioning or program syn- thesis to name a few can be abstracted as structured prediction problems. For these problems, the search space is well-defined but extremely large ...
  • Computational methods for creative inspiration in thematic typography and dance 

    Tendulkar, Purva Milind (Georgia Institute of Technology, 2020-08-04)
    As progress in technology continues, there is a need to adapt and upscale tools used in artistic and creative processes. This can either take the form of generative tools which can provide inspiration to artists, human-AI ...
  • Search-based collision-free motion planning for robotic sculpting 

    Jain, Abhinav (Georgia Institute of Technology, 2020-07-28)
    In this work, I explore the task of robot sculpting. I propose a search-based planning algorithm to solve the problem of sculpting by material removal with a multi-axis manipulator. I generate collision free trajectories ...
  • Extracting ICS models from malware via concolic analysis 

    Kilger, Fabian (Georgia Institute of Technology, 2020-07-28)
    While there has been significant progress in automated malware analysis, the focus of prior work has been mostly on programs written in C/C++. Advanced malware such as the Triton malware, however, also employ Python which ...
  • Deep-learning for automated diatom detection and identification for the ecological diagnosis of fresh-water environments 

    Faure-Giovagnoli, Pierre Thomas (Georgia Institute of Technology, 2020-07-29)
    Diatoms are a type of unicellular microalgae found in all aquatic environments. Their great diversity and ubiquity make these organisms recognized bio-indicators for monitoring the ecological status of watercourses, notably ...
  • Enabling parallelism and optimizations in data mining algorithms for power-law data 

    Mandal, Ankush (Georgia Institute of Technology, 2020-07-27)
    Today's data mining tasks aim to extract meaningful information from a large amount of data in a reasonable time mainly via means of --- a) algorithmic advances, such as fast approximate algorithms and efficient learning ...
  • Scaling synchronization primitives 

    Kashyap, Sanidhya (Georgia Institute of Technology, 2020-07-28)
    Over the past decade, multicore machines have become the norm. A single machine is capable of having thousands of hardware threads or cores. Even cloud providers offer such large multicore machines for data processing ...
  • Deep representation learning on hypersphere 

    Liu, Weiyang (Georgia Institute of Technology, 2020-07-27)
    How to efficiently learn discriminative deep features is arguably one of the core problems in deep learning, since it can benefit a lot of downstream tasks such as visual recognition, object detection, semantic segmentation, ...
  • Finding race conditions in kernels: The symbolic way and the fuzzy way 

    Xu, Meng (Georgia Institute of Technology, 2020-07-28)
    The scale and pervasiveness of concurrent software pose challenges for security researchers: race conditions are more prevalent than ever, and the growing software complexity keeps exacerbating the situation -- expanding ...
  • Data- and communication-centric approaches to model and design flexible deep neural network accelerators 

    Kwon, Hyouk Jun (Georgia Institute of Technology, 2020-07-23)
    Deep neural network (DNN) accelerators, which are specialized hardware for DNN inferences, enabled energy-efficient and low-latency DNN inferences. To maximize the efficiency (energy efficiency, latency, and throughput) ...
  • Measuring the effect of user experience and engagement on learning using interactive simulations 

    Tomlinson, Brianna J. (Georgia Institute of Technology, 2020-07-21)
    Previous studies have explored the best methods to measure emotional, cognitive, and physical engagement, but these methods have not been applied to fully understand the impact of multimodal interactive simulations on ...
  • Learning Nash equilibria in zero-sum stochastic games via entropy-regularized policy approximation 

    Zhang, Qifan (Georgia Institute of Technology, 2020-07-27)
    In this thesis, we explore the use of policy approximation for reducing the computational cost of learning Nash Equilibria in Multi-Agent Reinforcement Learning. Existing multi-agent reinforcement learning methods are ...
  • Crossbar scheduling algorithms for input-queued switches 

    Gong, Long (Georgia Institute of Technology, 2020-07-08)
    Many of today's switches and routers adopt an input-queued crossbar architecture to interconnect the input ports with the output ports. Such a switch needs to compute a crossbar schedule, or a matching, between the input ...
  • Human-guided task transfer for interactive robots 

    Fitzgerald, Tesca Kate (Georgia Institute of Technology, 2020-07-06)
    Adaptability is an essential skill in human cognition, enabling us to draw from our extensive, life-long experiences with various objects and tasks in order to address novel problems. To date, robots do not have this kind ...
  • Digital self-harm: Implications of eating disordered behaviors online 

    Pater, Jessica A. (Georgia Institute of Technology, 2020-07-21)
    It is estimated that 10%-20% of the US population will struggle with an eating disorder at some point in their lifetime [258]. Eating disorders is a complex set of psychiatric disorders that, regardless of classification, ...
  • Asynchronous versions of Jacobi, multigrid, and Chebyshev solvers 

    Wolfson-Pou, Jordi (Georgia Institute of Technology, 2020-07-06)
    Iterative methods are commonly used for solving large, sparse systems of linear equations on parallel computers. Implementations of parallel iterative solvers contain kernels (e.g., parallel sparse matrix-vector products) ...
  • Mitigating interconnect and end host congestion in modern networks 

    Zhao, Yimeng (Georgia Institute of Technology, 2020-07-06)
    One of the most critical building blocks of the Internet is the mechanism to mitigate network congestion. While existing congestion control approaches have served their purpose well in the last decades, the last few years ...
  • Efficient trajectory and policy optimization using dynamics models 

    Yan, Xinyan (Georgia Institute of Technology, 2020-07-22)
    Data-driven approaches hold the promise of creating the next wave of robots that can perform diverse tasks and adapt to unstructured environments. However, gathering data of physical systems is often a labor-intensive, ...
  • Learning dynamic processes over graphs 

    Trivedi, Rakshit (Georgia Institute of Technology, 2020-07-09)
    Graphs appear as a versatile representation of information across domains spanning social networks, biological networks, transportation networks, molecular structures, knowledge networks, web information network and many ...
  • Extending the lifecycle of IoT devices using selective deactivation 

    Hesse, Michael Winfried (Georgia Institute of Technology, 2020-05-17)
    IoT devices are known for long-lived hardware and short-lived software support by the vendor, which sets the wrong security incentives for users of expensive IoT systems. In order to mitigate as many known vulnerabilities ...

View more