Search Constraints

Start Over
Filtering by: Creator Wang, B. Remove constraint Creator: Wang, B. Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • Using Change Representations to Analyze Properties of Variational Software

    Creator:
    Wang, Xiangyu
    Abstract:
    Appropriate representations of variational software simplify the analysis of their properties.This thesis proposes tailored representations of two kinds variational softwares: difference files of merge commits in Git and feature models. For the former, we use the Choice Edit Model, which is based on the choice calculus, to represent changes introduced...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Xiangyu Wang for the degree of

  • Contributions to a Java recommender system

    Creator:
    Wang, Yun
    Abstract:
    Identifying the most relevant items in an e-commerce site is becoming more and more difficult nowadays because of the heavy overload of information. A Java Recommender System that uses Collaborative Filtering techniques has been developed to reduce such information overload and even personalize the information to the individual’s preference. The...
    Resource Type:
    Capstone Project
    Full Text:
    CCoonnttrriibbuuttiioonnss ttoo aa JJaavvaa RReeccoommmmeennddeerr SSyysstteemm Yun Wang

  • Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

    Creator:
    Wang, Xinyao
    Abstract:
    Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Xinyao Wang for the degree

  • Protein geometry and conformation resource database

    Creator:
    Wang, Nan
    Abstract:
    This project is about helping protein naturalists understand the protein structure. The database system developed here provides a convenient tool for scientists to explore conformational information in a database of known structures and thereby provide researchers with a deeper and wider view of the empirical data. In this way, it...
    Resource Type:
    Capstone Project
    Full Text:
    PROJECT Submitted to Oregon State University Nan Wang In partial fulfillment of the requirement of

  • 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:
    AN ABSTRACT OF THE THESIS OF Xin Wang for the degree of Doctor

  • Logic sampling, likelihood weighting and AIS-BN : an exploration of importance sampling

    Creator:
    Wang, Haiou
    Abstract:
    Logic Sampling, Likelihood Weighting and AIS-BN are three variants of stochastic sampling, one class of approximate inference for Bayesian networks. We summarize the ideas underlying each algorithm and the relationship among them. The results from a set of empirical experiments comparing Logic Sampling, Likelihood Weighting and AIS-BN are presented. We...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Haiou Wang for the degree of

  • A grading tool for the Translators course

    Creator:
    Wang, Haiyan
    Abstract:
    This report addresses the design and implementation of an internet­-based grading tool for the "Translators" course. The motivation is to avoid exposing the instructor's Java byte-code to possible reverse­-engineering tools and enable students to submit their homework vir­tually from any machine across the internet. This tool is intended to replace...
    Resource Type:
    Capstone Project
    Full Text:
    ) A Grading Tool for the Translators Course Haiyan Wang

  • On sequential/parallel matrix array languages

    Creator:
    Wang, Patrick Shen-Pei
    Abstract:
    A new system called sequential/parallel matrix grammars for two-dimensional pattern processing is introduced and studied. Miscellaneous language operations such as union, catenation (row and column), Kleene's closure (row and column) and substitutions are investigated. The equivalence of sequential/parallel matrix languages and finite-turn repetitive checking automata is established. Hierarchies for both...
    Resource Type:
    Dissertation
    Full Text:
    ABSTRACT OF THE THESIS OF Patrick Shen-Pei Wang for the degree of Doctor of Philosophy in Computer

  • An Exploration Into The Ever-changing Expanse of Non-periodic Tilings

    Creator:
    Tassin, Ian
    Abstract:
    This paper synthesizes various works Wang tiles up to this point, including: the reduction from the Halting Problem to Wang Tiling Problem and notions around various aspects of periodicity, including minimal period, aperiodicity, and axis-aligned periodicity. Additionally it includes new work, including: a proof that a tiling can be periodic...
    Resource Type:
    Honors College Thesis
    Full Text:
    synthesizes various works Wang tiles up to this point, including: the reduction from the Halting Problem to

  • Two Sides of a Coin: Adversarial-Based Image Privacy and Defending Against Adversarial Perturbations for Robust CNNs

    Creator:
    Rajabi, Arezoo
    Abstract:
    Emergence of highly accurate Convolutional Neural Networks (CNNs) with the capability to process large datasets, has led to their popularity in many applications, including safety/security-sensitive (e.g. disease recognition, self-driving cars). Despite the high accuracy of convolutional neural networks, they have been found to be susceptible to adversarial noise added to...
    Resource Type:
    Dissertation
    Full Text:
    CNNs Abstract approved: Rakesh B. Bobba Emergence of highly accurate Convolutional Neural Networks