Now showing items 652-671 of 1071

    • A neurally based vision model for line extraction and attention 

      Ungruh, Joachim (Georgia Institute of Technology, 1992)
    • Neuro-general computing an acceleration-approximation approach 

      Yazdan Bakhsh, Amir (Georgia Institute of Technology, 2018-07-30)
      A growing number of commercial and enterprise systems rely on compute and power intensive tasks. While the demand of these tasks is growing, the performance benefits from general-purpose platforms are diminishing. Without ...
    • New abstractions and mechanisms for virtualizing future many-core systems 

      Kumar, Sanjay (Georgia Institute of Technology, 2008-07-08)
      To abstract physical into virtual computing infrastructures is a longstanding goal. Efforts in the computing industry started with early work on virtual machines in IBM's VM370 operating system and architecture, continued ...
    • New approaches to integer programming 

      Chandrasekaran, Karthekeyan (Georgia Institute of Technology, 2012-06-28)
      Integer Programming (IP) is a powerful and widely-used formulation for combinatorial problems. The study of IP over the past several decades has led to fascinating theoretical developments, and has improved our ability to ...
    • New constructions of cryptographic pseudorandom functions 

      Banerjee, Abhishek (Georgia Institute of Technology, 2015-07-02)
      Pseudorandom functions (PRFs) are the building blocks of symmetric-key cryptography. Almost all central goals of symmetric cryptography (e.g., encryption, authentication, identification) have simple solutions that make ...
    • New formulations for active learning 

      Ganti Mahapatruni, Ravi Sastry (Georgia Institute of Technology, 2014-01-10)
      In this thesis, we provide computationally efficient algorithms with provable statistical guarantees, for the problem of active learning, by using ideas from sequential analysis. We provide a generic algorithmic framework ...
    • New insights on the power of active learning 

      Berlind, Christopher (Georgia Institute of Technology, 2015-07-22)
      Traditional supervised machine learning algorithms are expected to have access to a large corpus of labeled examples, but the massive amount of data available in the modern world has made unlabeled data much easier to ...
    • New paradigms for approximate nearest-neighbor search 

      Ram, Parikshit (Georgia Institute of Technology, 2013-07-02)
      Nearest-neighbor search is a very natural and universal problem in computer science. Often times, the problem size necessitates approximation. In this thesis, I present new paradigms for nearest-neighbor search (along with ...
    • New results on discrete-time time-varying linear systems 

      Hafiz, Khaled Mohammad (Georgia Institute of Technology, 1975)
    • New support vector machine formulations and algorithms with application to biomedical data analysis 

      Guan, Wei (Georgia Institute of Technology, 2011-06-13)
      The Support Vector Machine (SVM) classifier seeks to find the separating hyperplane wx=r that maximizes the margin distance 1/||w||2^2. It can be formalized as an optimization problem that minimizes the hinge loss Ʃ[subscript ...
    • New tools for unsupervised learning 

      Xiao, Ying (Georgia Institute of Technology, 2014-08-21)
      In an unsupervised learning problem, one is given an unlabelled dataset and hopes to find some hidden structure; the prototypical example is clustering similar data. Such problems often arise in machine learning and ...
    • Non-photorealistic rendering with coherence for augmented reality 

      Chen, Jiajian (Georgia Institute of Technology, 2012-07-16)
      A seamless blending of the real and virtual worlds is key to increased immersion and improved user experiences for augmented reality (AR). Photorealistic and non-photorealistic rendering (NPR) are two ways to achieve this ...
    • Nonnegative matrix and tensor factorizations, least squares problems, and applications 

      Kim, Jingu (Georgia Institute of Technology, 2011-11-14)
      Nonnegative matrix factorization (NMF) is a useful dimension reduction method that has been investigated and applied in various areas. NMF is considered for high-dimensional data in which each element has a nonnegative ...
    • Nonnegative matrix factorization for clustering 

      Kuang, Da (Georgia Institute of Technology, 2014-07-01)
      This dissertation shows that nonnegative matrix factorization (NMF) can be extended to a general and efficient clustering method. Clustering is one of the fundamental tasks in machine learning. It is useful for unsupervised ...
    • Novel document representations based on labels and sequential information 

      Kim, Seungyeon (Georgia Institute of Technology, 2015-07-23)
      A wide variety of text analysis applications are based on statistical machine learning techniques. The success of those applications is critically affected by how we represent a document. Learning an efficient document ...
    • Novel gestures for wearables 

      Zhang, Cheng (Georgia Institute of Technology, 2018-04-09)
      Wearable computing is an inevitable part of the next generation of computing [abowd2016beyon]. Compared with traditional computers (e.g., laptop, smartphones), wearable devices are much smaller, creating new challenges for ...
    • Novel Skeletal Representation for Articulated Creatures 

      Brostow, Gabriel Julian (Georgia Institute of Technology, 2004-04-12)
      This research examines an approach for capturing 3D surface and structural data of moving articulated creatures. Given the task of non-invasively and automatically capturing such data, a methodology and the associated ...
    • Novel spatial query processing techniques for scaling location based services 

      Pesti, Peter (Georgia Institute of Technology, 2012-11-12)
      Location based services (LBS) are gaining widespread user acceptance and increased daily usage. GPS based mobile navigation systems (Garmin), location-related social network updates and "check-ins" (Facebook), location-based ...
    • Numerical and analytical studies of quantum error correction 

      Tomita, Yu (Georgia Institute of Technology, 2014-04-11)
      A reliable large-scale quantum computer, if built, can solve many real-life problems exponentially faster than the existing digital devices. The biggest obstacle to building one is that they are extremely sensitive and ...
    • Numerical and streaming analyses of centrality measures on graphs 

      Nathan, Eisha (Georgia Institute of Technology, 2018-03-28)
      Graph data represent information about entities (vertices) and the relationships or connections between them (edges). In real-world networks today, new data are constantly being produced, leading to the notion of dynamic ...