Now showing items 1-20 of 91

    • 3-D Object Segmentation from Motion Cues 

      Herbst, Evan
      In this work we tackle the problem of segmenting rigid objects using various types of motion cues. The setting is that of personal robotics, in which robots generally have cameras and arms, and are capable of manipulating ...
    • Action Recognition and Prediction with Applications to Medical Diagnosis and Daily Living 

      Soran, Bilge
      The purpose of this research is to explore the possible ways of improving people’s lives using information from static or egocentric (wearable) cameras. The usage of this information can be diagnostic or preventive. In a ...
    • Active Learning and Submodular Functions 

      Guillory, Andrew Russell (2012-09-13)
      Active learning is a machine learning setting where the learning algorithm decides what data is labeled. Submodular functions are a class of set functions for which many optimization problems have efficient exact or ...
    • Algorithmic Approaches to Detecting Interviewer Fabrication in Surveys 

      Birnbaum, Benjamin (2013-02-25)
      Surveys are one of the principal means of gathering critical data from low-income regions. Bad data, however, may be no better--or worse--than no data at all. Interviewer data fabrication, one cause of bad data, is an ...
    • Applications of Metric Embeddings in Solving Combinatorial Problems 

      Moharrami, Mohammad (2013-11-14)
      Metric embeddings constitute one of the fundamental tools for exploiting the underlying geometric structure of many combinatorial problems. In this dissertation we study some of the applications of metric embeddings in the ...
    • Approaches to Food Journaling on Mobile Devices 

      Andrew, Adrienne Hope (2013-04-17)
      A healthy diet has the power to both prevent and heal disease, and the high rates of lifestyle- and diet-related disease in America indicates the need for tools to help improve diet. Self-monitoring one's food intake is ...
    • Approximate Acceleration for a Post Multicore Era 

      Esmaeilzadeh, Hadi (2013-11-14)
      Starting in 2004, the microprocessor industry has shifted to multicore scaling--increasing the number of cores per die each technology generation--as its principal strategy for continuing performance growth. This work first ...
    • Automated Discovery and Learning of Complex Movement Behaviors 

      Mordatch, Igor
      In order to create useful physical robots, tell narratives in animated films and interactive games, or understand the underlying principles behind human movement, it is necessary to synthesize movement behaviors with the ...
    • Automatic Scaffolding for Procedural Learning 

      Andersen, Erik
      A key challenge in education is how provide support that is tailored to the learner's individual needs. Effective teachers and curricula typically provide such support, often referred to as instructional scaffolding, through ...
    • Automatic Scaffolding for Procedural Learning 

      Andersen, Erik
      A key challenge in education is how provide support that is tailored to the learner's individual needs. Effective teachers and curricula typically provide such support, often referred to as instructional scaffolding, through ...
    • Automating Stochastic Optimal Control 

      Dvijotham, Krishnamurthy (2014-04-30)
      Stochastic Optimal Control is an elegant and general framework for specifying and solving control problems. However, a number of issues have impeded its adoption in practical situations. In this thesis, we describe algorithmic ...
    • Avoiding State-Space Explosion in Multithreaded Programs with Input-Covering Schedules and Symbolic Execution 

      Bergan, Thomas (2014-04-30)
      This dissertation makes two high-level contributions: First, we propose an algorithm to perform symbolic execution of multithreaded programs from arbitrary program contexts. We argue that this can enable more efficient ...
    • Backscatter Protocols and Energy-Efficient Computing for RF-Powered Devices 

      Buettner, Michael (2013-02-25)
      RF-powered computers operate using energy they harvest from radio frequency (RF) signals. Compared to battery powered devices, they have the advantages of being small and long-lived as they do not need to carry an onboard ...
    • Building Behavioral Experimentation Engines 

      Liu, Yun-En
      Human behavior is an incredibly complex topic, given the variation between individuals and the many ways we can be influenced by our environment. This complexity, combined with the difficulty and expense of running experiments ...
    • Characterizing and Improving Web Page Load Times 

      Wang, Xiao
      Web page load time (PLT) is a key performance metric that many techniques aim to improve. PLT is much slower than lower-level latencies, but the reason was not well understood. This dissertation first characterizes theWeb ...
    • Computational Generation of Terrestrial Animal Locomotion 

      Wampler, Kevin (2013-04-17)
      While the animation of humans is a well established topic in computer graphics, the animation of animals remains far less explored. Part of this is because in contrast to the wealth of easily obtainable motion data for ...
    • CoSolve: A Novel System for Engaging Users in Collaborative Problem-Solving 

      Fan, Sandra Benxin (2013-07-23)
      In an increasingly connected world, there are ever more opportunities for online collaboration. As the potential for more collaborators grows, so does the complexity of such communications. Problem solving, already a ...
    • Designing for Effective End-User Interaction with Machine Learning 

      Amershi, Saleema (2013-02-25)
      End-user interactive machine learning is a promising tool for enhancing human capabilities with data. Recent work has shown that we can create specific applications that employ end-user interactive machine learning. However, ...
    • Deterministic Execution for Arbitrary Multithreaded Programs 

      Devietti, Joseph (2013-04-17)
      Nondeterminism is one of the main reasons that parallel programming is so difficult. Bugs can vanish when programs are rerun or run under a debugger, thwarting attempts at their removal. Stress-testing is a common practice ...
    • Discovery and Applications of Bacterial Noncoding RNAs 

      Tseng, Huei-Hun Elizabeth (2013-02-25)
      Noncoding RNAs (ncRNAs) are functional transcripts that do not code for proteins. Many of them play indispensible roles in the cell. For example, the ribosomal RNAs make up the ribosome that is the factory for making ...