Search Constraints

Start Over
Filtering by: Creator Little, Stefan A. Remove constraint Creator: Little, Stefan A. Degree Field Computer Science Remove constraint Degree Field: Computer Science Rights Statement In Copyright Remove constraint Rights Statement: In Copyright

Search Results

  • Infant Hand Detection and Tracking

    Creator:
    Mishra, Shridhar
    Abstract:
    Hand detection is a fundamental step for many hand-related computer vision tasks, such as gesture recognition, hand pose estimation, hand sign language translation, and so on. However, robustly detecting hands is a challenging task because of drastic changes in appearance based on finger articulation and changes in lighting conditions, camera...
    Resource Type:
    Masters Thesis
    Full Text:
    Detection and Tracking Abstract approved: Stefan Lee Hand detection is a fundamental step for many hand

  • Open, online, interactive visualizations for learning about Gaussian mixture models

    Creator:
    Allen, Stuart
    Abstract:
    We construct a website to explain how Gaussian mixture models can be optimized using the expectation maximization algorithm. Previous free, online material on this process has been extremely limited. All sources surveyed failed to entirely describe our identified criteria for an in-depth description and useful visualizations. After surveying a variety...
    Resource Type:
    Honors College Thesis
    Full Text:
    Gaussian Mixture Models Abstract approved: Stefan Lee We construct a website to explain how Gaussian

  • Semantic embodied navigation : developing agents that navigate from language and vision

    Creator:
    Krantz, Jacob
    Abstract:
    Autonomous robotic agents are on their way to becoming in-home personal assistants, construction assistants, and warehouse workers. The degree of autonomy of such systems is reflected by the manner in which we specify goals to them; the abstraction of low-level commands to high-level goals goes hand-in-hand with increased autonomy. In...
    Resource Type:
    Dissertation
    Full Text:
    Embodied AI Workshop for giving me a conference home and community. To my PhD committee, Stefan Lee

  • Explaining and Improving Neural Machine Translation

    Creator:
    Yang, Yilin
    Abstract:
    Machine Translation, the task of automatically translating between human languages has been studied for decades. This task is used to be solved by count-based statistical models, e.g. Phrase-based Statistical Machine Translation (PBSMT), which solves the translation problem by separately training a statistical language model and a translation model. Recently, Neural...
    Resource Type:
    Dissertation
    Full Text:
    : Explaining and Improving Neural Machine Translation Abstract approved: Prasad Tadepalli & Stefan Lee

  • 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

  • Little Smalltalk in Java

    Creator:
    Pandrangi, Phani Srikanth
    Abstract:
    Little Smalltalk is a small, reasonably fast, easy-to-understand, easy-to-modify Smalltalk system. The system was originally developed in 1984 as a part of an implementation project to develop a minimal Smalltalk system, closely resembling Smalltalk-80. The sys­tem was developed in C. The current project is an experiment to port the Little...
    Resource Type:
    Capstone Project
    Full Text:
    ) Little Smalltalk in Java Phani Srikanth Pandrangi 1.0 Abstract Little Smalltalk is a small

  • Analysis of Convolutional Neural Network Image Pre-processing Methods

    Creator:
    Jacobsen, Matthew
    Abstract:
    Oceanic plankton have both a large impact on our oceans health and atmo- spheric balance of Co2. The overall health of planktonic life is determined by many physical, chemical, and ecological factors, that drive taxonomic abundances and the relative amount of non-living biomass called detritus. Recent advances in microscopic imaging...
    Resource Type:
    Honors College Thesis
    Full Text:
    Matthew Jacobsen A THESIS submitted to Oregon State University Honors College in partial fulfillment

  • Sensorless Localization for Robots and Wheelchairs

    Creator:
    Subramanian, Ashwin
    Abstract:
    Despite an increase in the number of people who rely on manual wheelchairs, there are still substantial economic barriers to affordable and accessible localization systems. As a result, there is a pressing need to build a versatile yet low cost localization system for manual wheelchairs. Such systems allow users to...
    Resource Type:
    Honors College Thesis
    Full Text:
    Wheelchairs by Ashwin Subramanian A THESIS submitted to Oregon State University Honors College in

  • Deep Learning Temporal Logic Specifications

    Creator:
    Hekkala, Claire M.
    Abstract:
    This thesis seeks to explain a new method of extracting temporal logic formulas from time series data using machine learning. Two strategies were followed during the development of this research: first, a generative adversarial network was combined with already-existing temporal logic extraction code by Belta. This was achieved by injecting...
    Resource Type:
    Honors College Thesis
    Full Text:
    Claire Hekkala A THESIS submitted to Oregon State University

  • Exploring Outlier Exposure Methods for Deep Margin-Based Anomaly Detection

    Creator:
    Noel, Thomas
    Abstract:
    In standard training regimes, one assumes that the classes presented to a model constitute all of the classes that the model will encounter when it is deployed. In real deployment scenarios, however, a model can sometimes encounter situations or objects that it has never seen. When these scenarios are safety-critical,...
    Resource Type:
    Capstone Project
    Full Text:
    Weng-Keen Wong In standard training regimes, one assumes that the classes presented to a model