Now showing items 559-578 of 1105

    • Landslide information service based on composition of physical and social information services 

      Musaev, Aibek (Georgia Institute of Technology, 2016-05-10)
      Modern world data come from an increasing number of sources, including data from physical sources like satellites and seismic sensors as well as social networks and web logs. While progress has been made in the filtering ...
    • Language features for fully distributed processing systems 

      Maccabe, Arthur Bernard (Georgia Institute of Technology, 1982)
    • Large scale machine learning for geospatial problems in computational sustainability 

      Robinson, David Caleb (Georgia Institute of Technology, 2020-05-14)
      The UN laid out 17 Sustainable Development Goals as part of the “The 2030 Agenda for Sustainable Development”. Each goal consists of broad targets - such as increasing the percentage of forested land (indicator 15.1.1) - ...
    • Lateral positioning of a monocular head-worn display 

      Haynes, Malcolm Gibran (Georgia Institute of Technology, 2017-08-25)
      Head-worn displays (HWDs) such as Google Glass are becoming more common. However, the optimal location for the display of such devices is an open question. Existing devices have displays located above, below, and in line ...
    • Learning adaptive reactive agents 

      Santamaria, Juan Carlos (Georgia Institute of Technology, 1997-08)
    • Learning an integrated hybrid image retrieval system 

      Jing, Yushi (Georgia Institute of Technology, 2012-01-06)
      Current Web image search engines, such as Google or Bing Images, adopt a hybrid search approach in which a text-based query (e.g. "apple") is used to retrieve a set of relevant images, which are then refined by the user ...
    • Learning by observing and understanding expert problem solving 

      Redmond, Michael Albert (Georgia Institute of Technology, 1992-12)
    • Learning descriptive models of objects and activities from egocentric video 

      Fathi, Alireza (Georgia Institute of Technology, 2013-06-13)
      Recent advances in camera technology have made it possible to build a comfortable, wearable system which can capture the scene in front of the user throughout the day. Products based on this technology, such as GoPro and ...
    • 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 ...
    • Learning embodied models of actions from first person video 

      Li, Yin (Georgia Institute of Technology, 2017-08-28)
      Advances in sensor miniaturization, low-power computing, and battery life have enabled the first generation of mainstream wearable cameras. Millions of hours of videos are captured by these devices every year, creating a ...
    • Learning from Observation Using Primitives 

      Bentivegna, Darrin Charles (Georgia Institute of Technology, 2004-07-13)
      Learning without any prior knowledge in environments that contain large or continuous state spaces is a daunting task. For robots that operate in the real world, learning must occur in a reasonable amount of time. Providing ...
    • Learning in public: information literacy and participatory media 

      Forte, Andrea (Georgia Institute of Technology, 2009-07-06)
      This research examines new systems of information production that are made possible by participatory media. Such systems bring about two critical information literacy needs for the general public: to understand new systems ...
    • Learning knowledge to support domain-independent narrative intelligence 

      Li, Boyang (Georgia Institute of Technology, 2015-01-09)
      Narrative Intelligence is the ability to craft, tell, understand, and respond appropriately to narratives. It has been proposed as a vital component of machines aiming to understand human activities or to communicate ...
    • Learning matrix and functional models in high-dimensions 

      Balasubramanian, Krishnakumar (Georgia Institute of Technology, 2014-06-20)
      Statistical machine learning methods provide us with a principled framework for extracting meaningful information from noisy high-dimensional data sets. A significant feature of such procedures is that the inferences made ...
    • 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 ...
    • Learning neural algorithms with graph structures 

      Dai, Hanjun (Georgia Institute of Technology, 2020-01-13)
      Graph structures, like syntax trees, social networks, and programs, are ubiquitous in many real world applications including knowledge graph inference, chemistry and social network analysis. Over the past several decades, ...
    • Learning over functions, distributions and dynamics via stochastic optimization 

      Dai, Bo (Georgia Institute of Technology, 2018-07-27)
      Machine learning has recently witnessed revolutionary success in a wide spectrum of domains. The learning objectives, model representation, and learning algorithms are important components of machine learning methods. To ...
    • Learning to walk using deep reinforcement learning and transfer learning 

      Yu, Wenhao (Georgia Institute of Technology, 2020-05-17)
      We seek to develop computational tools to reproduce the locomotion of humans and animals in complex and unpredictable environments. Such tools can have significant impact in computer graphics, robotics, machine learning, ...
    • Learning without labels and nonnegative tensor factorization 

      Balasubramanian, Krishnakumar (Georgia Institute of Technology, 2010-04-08)
      Supervised learning tasks like building a classifier, estimating the error rate of the predictors, are typically performed with labeled data. In most cases, obtaining labeled data is costly as it requires manual labeling. ...
    • Level of detail management 

      Watson, Benjamin A. (Benjamin Allen) (Georgia Institute of Technology, 1997-08)