Search Constraints

Start Over
Filtering by: Creator Gamroth, M. J. (Michael J.) Remove constraint Creator: Gamroth, M. J. (Michael J.) Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • Porting and optimizing a routing library for Dataparallel C on the nCUBE 2 system

    Creator:
    Sivaramapuram, Krishna
    Abstract:
    Dataparallel C has been designed for various kinds of architectures and was devel­oped jointly at University of New Hampshire and Oregon State University. This project dealt with porting the libraries to the nCUBE 2 system and helping a user compile his programs on nCUBE 2 directly from a Sun workstation...
    Resource Type:
    Capstone Project
    Full Text:
    Professor : Dr. Michael J. Quinn Minor Professor : Dr. Lawrence A. Crowl Committee Member : Dr. Tadepalli

  • A C* development environment for the Meiko CS-2 multicomputer

    Creator:
    Zhang, Chung
    Abstract:
    With sequential computing technology reaching its speed limits, parallel processing is emerg­ing as the key to very-high-speed computation. However, developing a parallel program is by no means a simple task; neither is analyzing the performance of parallel programs. C* is a high-level data-parallel language that hides explicit message passing and...
    Resource Type:
    Capstone Project
    Full Text:
    Corvallis, OR 97331 zhangch@research. cs. orst. edu Major Professor: Dr. Michael J. Quinn Minor

  • Physical activity recognition of free-living data using change-point detection algorithms and hidden Markov models

    Creator:
    Anderson, Michael M.
    Abstract:
    Physical activity recognition using accelerometer data is a rapidly emerging field with many real-world applications. Much of the previous work in this area has assumed that the accelerometer data has already been segmented into pure activities, and the activity recognition task has been to classify these segments. In reality, activity...
    Resource Type:
    Masters Thesis
    Full Text:
    Change-Point Detection Algorithms and Hidden Markov Models AN ABSTRACT OF THE THESIS OF Michael M

  • Learning MDP action models via discrete mixture trees

    Creator:
    Wynkoop, Michael S.
    Abstract:
    This thesis addresses the problem of learning dynamic Bayesian network (DBN) models to support reinforcement learning. It focuses on learning regression tree models of the conditional probability distributions of the DBNs. Existing algorithms presume that the stochasticity in the domain can be modeled as a deterministic function with additive noise....
    Resource Type:
    Masters Thesis
    Full Text:
    OF Michael S. Wynkoop for the degree of Masters of Science in Computer Science presented on June 9

  • Analytical Methods for Improving Causal Inference

    Creator:
    Sinha, Meghamala
    Abstract:
    Causal inference is an important analytical tool to bridge the gap between prediction and decision-making. However, learning a causal network solely from data is a challenging task. In this work, various techniques have been explored for a better and improved causal network learning from data. Firstly, the problem of learning...
    Resource Type:
    Dissertation
    Full Text:
    distribution of p after intervention is: p(V1, ..., Vn) = ∏ Vi∈Oe pi(Vi | Pa(Vi)) · ∏ Vj∈Ie p′j(Vj | Pa(Vj

  • Auxiliary Tasks for Efficient Learning of Point-Goal Navigation

    Creator:
    Desai, Saurabh Satish
    Abstract:
    Top-performing approaches to embodied AI tasks like point-goal navigation often rely on training agents via reinforcement learning over tens of millions (or even billions) of experiential steps – learning neural agents that map directly from visual observations to actions. In this work, we question whether these extreme training durations are...
    Resource Type:
    Masters Thesis
    Full Text:
    for Efficient Learning of Point-Goal Navigation Abstract approved: Stefan M. Lee Top-performing

  • Inclusive Software Design and Its Methods for Beyond-WIMP User Interfaces

    Creator:
    Fallatah, Abrar
    Abstract:
    While digital inclusivity researchers and software practitioners have been trying to address exclusion biases in Windows, Icons, Menus, and Pointers (WIMP) user interfaces (UIs) for a long time, little has been done to investigate if and how inclusive software design and its methods that have been devised for WIMP UIs...
    Resource Type:
    Dissertation

  • Interactive fault localization techniques to empower the debugging efforts of end-user programmers

    Creator:
    Ruthruff, Joseph Ronald
    Abstract:
    End users develop more software than any other group of programmers, using software authoring devices such as e-mail filtering editors, by-demonstration macro builders, and spreadsheet environments. Despite this, there has been only a little research on finding ways to help these programmers with the dependability of the software they create....
    Resource Type:
    Masters Thesis
    Full Text:
    : Margaret M. Burnett End users develop more software than any other group of programmers, using software

  • Resource placement, data rearrangement, and Hamiltonian cycles in torus networks

    Creator:
    Bae, Myung Mun
    Abstract:
    Many parallel machines, both commercial and experimental, have been/are being designed with toroidal interconnection networks. For a given number of nodes, the torus has a relatively larger diameter, but better cost/performance tradeoffs, such as higher channel bandwidth, and lower node degree, when compared to the hypercube. Thus, the torus is...
    Resource Type:
    Dissertation
    Full Text:
    this type and a binary vector of length b m with weight b; in a given configuration, if the j-th box

  • Model-based approximation methods for reinforcement learning

    Creator:
    Wang, Xin
    Abstract:
    The thesis focuses on model-based approximation methods for reinforcement learning with large scale applications such as combinatorial optimization problems. First, the thesis proposes two new model-based methods to stablize the value–function approximation for reinforcement learning. The first one is the BFBP algorithm, a batch-like reinforcement learning process which iterates between...
    Resource Type:
    Dissertation
    Full Text:
    Lipschitz Continuity of ∇M ∞ θk J(θk) . . . . . . . . . 199 LIST OF FIGURES Figure Page 2.1 Performance