Search Constraints

Start Over
Filtering by: Creator Edwards, Daniel K. Remove constraint Creator: Edwards, Daniel K. Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • Out of the Mouths of Users : Examining User-Developer Feedback Loops Facilitated by App Stores

    Creator:
    Bailey, Kendall
    Abstract:
    Application Stores, such as the iTunes App Store, give developers access to their users’ complaints and requests in the form of application reviews. However, little is known about how developers are responding to application reviews. Without such knowledge developers, users, Application Stores, and researchers could make incorrect assumptions. To address...
    Resource Type:
    Masters Thesis

  • Understanding Software Development and Testing Practices

    Creator:
    Hilton, Michael
    Abstract:
    A bad software development process leads to wasted effort and inferior products. In order to improve a software process, it must be first understood. In this work I focus on understanding software processes. The first process we seek to understand is Continuous Integration (CI). CI systems automate the compilation, building,...
    Resource Type:
    Dissertation
    Full Text:
    Software Development and Testing Practices Abstract approved: Daniel Dig A bad software development

  • Automatic Classification of Ultrasonic Harbor Porpoise Clicks in a Varying Noise Environment

    Creator:
    De Leon, Daniel
    Abstract:
    This study compares three approaches in the design of an autonomous machine listening agent that predicts harbor porpoise ultrasonic echolocation clicks in diverse noise environments. Considering the temporal variations of noisy coastal ocean soundscapes which the harbor porpoises inhabit, we propose a leave-one-day-out (LODO) cross-validation strategy in the training of...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Daniel De Leon for

  • Shrunken learning rates do not improve AdaBoost on benchmark datasets

    Creator:
    Forrest, Daniel L. K.
    Abstract:
    Recent work has shown that AdaBoost can be viewed as an algorithm that maximizes the margin on the training data via functional gradient descent. Under this interpretation, the weight computed by AdaBoost, for each hypothesis generated, can be viewed as a step size parameter in a gradient descent search. Friedman...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Daniel L. K. Forrest for the

  • Partitioning-Guided K-Means for Effective Empty Cluster Resolution in Extreme Model Compression

    Creator:
    Huang, Tianhong
    Abstract:
    Compactness in deep learning can be critical to a model’s viability in low-resource applications, and a common approach to extreme model compression is quantization. We consider Iterative Product Quantization (iPQ) with Quant-Noise [Fan et al., 2020] to be state-of-the-art in this area, but this quantization framework suffers from preventable inference...
    Resource Type:
    Masters Thesis
    Full Text:
    , Nenad Mladenović, and Daniel Nobre Pinheiro. On Strategies to Fix Degenerate k-means Solutions. Journal

  • Using signaling to aid computer program comprehension

    Creator:
    Gellenbeck, Edward M.
    Abstract:
    Guidelines for using style to improve computer program comprehension have often been proposed without empirical testing. This thesis reports on the results of three controlled experiments that investigated ways program style may be used to aid comprehension of source code listings. Experiments 1 and 2 were conducted using advanced computer...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE THESIS OF Edward M. Gellenbeck for the degree of Doctor of Philosophy in Computer

  • Volume minimized generalized cross entropy for learning with label noise

    Creator:
    Wolnick, Daniel
    Abstract:
    The types and rates of label noise in real-world data sets present a challenge to machine learning projects. In this thesis, we propose a novel approach to address this issue. Our method combines a noise modelling technique for correcting label noise across the entire data set with a robust loss...
    Resource Type:
    Honors College Thesis
    Full Text:
    with Label Noise By Daniel Wolnick A THESIS submitted to Oregon State University Honors College

  • Disjunctions in forward chaining logic programming

    Creator:
    Corpron, Daniel R.
    Abstract:
    A forward-chaining logic programming system (FORLOG) has been developed at Oregon State University. This system coupled with an assumption-based truth maintenance system (ATMS), provides an alternative to the logic programming paradigm of backward-chaining with Horn clauses. To compare FORLOG to this paradigm, we define a subset of FORLOG, called mini-FORLOG,...
    Resource Type:
    Masters Thesis
    Full Text:
    Abstract of the Thesis of Daniel R. Corpron for the degree of Master of Science in Computer Science

  • LacEDAemon : a programming environment for the multiparadigm language leda

    Creator:
    Pandey, Rajeev K.
    Abstract:
    Multiparadigm programming languages are a recent development in the realm of programming languages. A multiparadigm programming language allows the use of multiple, differing programming paradigms without departing from a single, unified linguistic framework. Multiparadigm programming languages are claimed to have benefits to both pedagogy and complex application creation. The beneficial...
    Resource Type:
    Dissertation
    Full Text:
    root.dvi AN ABSTRACT OF THE THESIS OF Rajeev K. Pandey for the degree of

  • Video Analysis : Techniques for Semi-Supervised Video Object Instance Segmentation and Tracking-by-Detection in the Wild

    Creator:
    Firl, Alrik K.
    Abstract:
    This thesis consists of two major components. The first part is concerned with video object instance segmentation (VOS), which is the task of assigning per-pixel labels perframe of a video sequence to indicate foreground object instance membership, given the first frame ground truth mask. VOS has myriad applications, from video...
    Resource Type:
    Masters Thesis
    Full Text:
    dimension [d x k] • X: the image features; this is a matrix of dimension [n x d] extracted from a CNN layer