Search Constraints

Start Over
Filtering by: Creator Merrifield, Matthew S. Remove constraint Creator: Merrifield, Matthew S. Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • Counterfactual States for Atari Agents via Generative Deep Learning

    Creator:
    Olson, Matthew L.
    Abstract:
    Although deep reinforcement learning agents have produced impressive results in many domains, their decision making is difficult to explain to humans. To address this problem, past work has mainly focused on explaining why an action was chosen in a given state. A different type of explanation that is useful is...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Matthew Lyle Olson for the

  • Characterizing and Addressing Dataset Shift with Deep Learning

    Creator:
    Olson, Matthew L.
    Abstract:
    This dissertation delves into understanding, characterizing, and addressing dataset shift in deep learning, a pervasive issue for deployed machine learning systems. Integral aspects of the problem are examined: We start with the use of counterfactual explanations in order to characterize the behavior of deep reinforcement learning agents in visual input...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Matthew L

  • A Study of Temporal Convolutional Neural Networks for Music Language Modeling as Applied to Automatic Music Transcription

    Creator:
    Meyn, Matthew
    Abstract:
    Automatic music transcription (AMT) is the task, given an acoustic representation of music, to recover a symbolic notation of the written notes expressed by the sound. Transcribing music with multiple notes sounding simultaneously is difficult for both humans and machines. Much existing work on AMT has focused on suitable acoustic...
    Resource Type:
    Capstone Project
    Full Text:
    AN ABSTRACT OF THE PROJECT REPORT OF Matthew Meyn for

  • 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

  • A Security Analysis of the Signal Protocol’s Group Messaging Capabilities in Comparison to Direct Messaging

    Creator:
    Jansen, Matthew L.
    Abstract:
    Signal is a multimedia messaging application developed by OpenWhisper Systems in 2015 which allows its users to communicate securely between one another through the use of a complex encryption scheme. The set of algorithms used in combination to provide the services of the Signal application to their users is called...
    Resource Type:
    Honors College Thesis
    Full Text:
    Capabilities in Comparison to Direct Messaging by Matthew Jansen A THESIS

  • The Implementation of Passive RFID Tags to Sample Volumetric Water Content for an Autonomous Irrigation System

    Creator:
    Guo, Matthew D.
    Abstract:
    The agricultural industry in the Western United States continues to possess issues of overwatering, accounting for over 80% of consumed water per year in the country. While technologies such as satellite imaging and sensor networks have slowly improved irrigation Best Management Practices to reduce superfluous water consumption, limitations associated with...
    Resource Type:
    Honors College Thesis
    Full Text:
    Volumetric Water Content for an Autonomous Irrigation System by Matthew Guo

  • A collaborative filtering algorithm and evaluation metric that accurately model the user experience

    Creator:
    McLaughlin, Matthew
    Abstract:
    "Collaborative filtering algorithms’ performances have been evaluated using a variety of metrics. These metrics, such as Mean Absolute Error and Precision, have often ignored recommendations for which they do not have data. Ignoring these recommendations has provided numbers which do not accurately represent the user experience. Qualitatively we have seen...
    Resource Type:
    Capstone Project
    Full Text:
    . 7 The uniform belief distribution s at the beginning of the Equation 7 can be thought of a null

  • 3D Voronoi Subdivision for Simulating Destructible and Granular Materials

    Creator:
    Clothier, Matthew M.
    Abstract:
    In many traditional computer graphics applications, rendered scenes typically utilize 3D meshes to represent objects within an environment. As the demand to further improve the realism of graphics applications increases, such as for movies and games, it is becoming more important to represent the inner volumes of object meshes. In...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Matthew

  • User Interface and Database for the Intuitive, Developmental And Research Oriented, Easy To Use, Affordable, And Low Volume (IDEAL) Bioreactor

    Creator:
    Litzinger, Jaelyn W.
    Abstract:
    Expensive pricing for laboratory bioreactors proves to be the main barrier-to-entry for lab-scale academic research. Most laboratory bioreactors are priced at $100K+ and require significant training to use, thereby limiting their accessibility. The IDEAL (Intuitive, Developmental And Research Oriented, Easy To Use, Affordable, And Low Volume) Bioreactor aims to solve...
    Resource Type:
    Honors College Thesis
    Full Text:
    Computer Science _____________________________________________________________________ Matthew Johnston

  • High school students' anticipated ROI in college and other career plans

    Creator:
    Kang, Kenneth
    Abstract:
    This study investigates the evaluation of Return on Investment (ROI) in education from the perspective of high school students, introducing a theoretical model that encompasses both financial and non-financial aspects, with a primary focus on the unique insights provided by high school students. Drawing from a literature review and survey-based...
    Resource Type:
    Honors College Thesis
    Full Text:
    _____________________________________________________________________ Matthew Hall, Committee Member, representing Marketing

  • Improving the accuracy and efficiency of bird song analysis with machine learning based event detection

    Creator:
    Mathew, Anju
    Abstract:
    Ornithology is an exciting field with novel research emerging everyday. Researchers in bioacoustics often spend hours within the wilderness recording bird calls to analyze later in their lab. The burden of sifting through hours of audio recordings from the field continues to remain a time-consuming and manual task, despite the...
    Resource Type:
    Honors College Thesis
    Full Text:
    of Electrical Engineering and Computer Science Matthew Orr, Committee Member, representing

  • Monte Carlo Tree Search with Fixed and Adaptive Abstractions

    Creator:
    Hostetler, Jesse A.
    Abstract:
    Monte Carlo tree search (MCTS) is a class of online planning algorithms for Markov decision processes (MDPs) and related models that has found success in challenging applications. In the online planning approach, the agent makes a decision in the current state by performing a limited forward search over possible futures...
    Resource Type:
    Dissertation
    Full Text:
    a lazy policy, since it delays computing the result of π(s) until it is called for. The two types

  • Convergence Analysis Framework for Fixed-Point Algorithms in Machine Learning and Signal Processing

    Creator:
    Vu, Trung
    Abstract:
    Iterative algorithms are simple yet efficient in solving large-scale optimization problems in practice. With a surge in the amount of data in past decades, these methods have become increasingly important in many application areas including matrix/tensor recovery, deep learning, data mining, and reinforcement learning. To optimize or improve iterative algorithms,...
    Resource Type:
    Dissertation
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 240 LIST OF FIGURES (Continued) Figure Page 7.1 Contour plot of ρ∞ as a 2-D function of ρr and ρs

  • Creating, Understanding and Applying Machine Learning Models of Multiple Species

    Creator:
    Griffioen, Arwen Twinkle E.
    Abstract:
    Many problems in ecology and conservation biology can be formulated and solved using machine learning algorithms for multi-label classification. This dissertation addresses three topics related to predicting the distributions of multiple species. It improves existing methods and proposes a new modeling paradigm to address the multi-species, multi-label problem. The first...
    Resource Type:
    Dissertation
    Full Text:
    (s) and do not necessarily reflect the views of the National Science Foundation

  • Multi-instance multi-label learning : algorithms and applications to bird bioacoustics

    Creator:
    Briggs, Forrest
    Abstract:
    We consider the problem of supervised classification of bird species from audio recordings in a real-world acoustic monitoring scenario (i.e. audio data is collected in the field with an omnidirectional microphone, without human supervision). Obtaining better data about bird activity can assist conservation efforts, and improve our understanding of their...
    Resource Type:
    Dissertation
    Full Text:
    University. We would also like to thank Matthew Betts, Sarah Frey, Adam Hadley, and Jay Sexsmith for their

  • Machine Learning for Precision Medicine: Application to Cancer Chemotherapy Response Prediction and Wound Healing Status Assessment

    Creator:
    Wei, Qi
    Abstract:
    Ph.D. candidate Qi Wei's thesis consists of two projects: Chemotherapy Project: a study based on the research paper "Predicting chemotherapy response of various cancer types using a variational auto-encoder approach" submitted to the bioRxiv preprint archive and accepted by the BMC bioinformatics; and Wound Monitor Project: implementing and assessing analytics...
    Resource Type:
    Dissertation
    Full Text:
    tremendous help in obtaining the dog wound image set. I would like to also thank Dr. Matthew Johnston, Dr

  • Adversarial Attacks in Natural Language Question-Answering

    Creator:
    Rahurkar, Prachi S.
    Abstract:
    Question Answering in natural language processing has achieved significant progress in recent years. Yet, training and testing set methodology to evaluate the language models has proved inadequate. Adversarial examples aid us in finding loopholes inside these models and provide insights into their inner workings. In this work, an evaluation based...
    Resource Type:
    Masters Thesis
    Full Text:
    Empirical Methods in Natural Lan- guage Processing (EMNLP), pages 1532–1543, 2014. [17] Matthew E. Peters

  • The Analysis of First Year Computer Science Design Documents

    Creator:
    Ernst, Shannon S.
    Abstract:
    Computer science is, at its core, about solving problems. The "Carry out the Plan" portion of problem solving is often examined and emphasized in CS 1 and CS 2, forgetting to emphasize the other important aspects of the problem solving process. This study focuses on the other problem-solving steps, which...
    Resource Type:
    Masters Thesis
    Full Text:
    function and/or classes relate(s) to each other Logic (L) Provided details for each function and/or

  • Towards Automating Type Changes

    Creator:
    Ketkar, Ameya S.
    Abstract:
    Developers frequently change the type of a program element and update all its references for performance, security, concurrency, library migration, or better maintainability. Despite type changes being a common program transformation, it is the least automated and the least studied. Manually performing type changes is tedious since the programmers have...
    Resource Type:
    Dissertation
    Full Text:
    replaced generic with specialized Java 8’s Functional Interfaces, the type changes in- volved 34 files

  • A Structural Theorem For Shortest Vertex-Disjoint Paths Computation in Planar Graphs

    Creator:
    Zafarani, Farzad
    Abstract:
    Given k terminal pairs (s₁,t₁),(s₂,t₂),..., (s[subscript k],t[subscript k]) in an edge-weighted graph G, the k Shortest Vertex-Disjoint Paths problem is to find a collection P₁, P₂,..., P[subscript k] of vertex-disjoint paths with minimum total length, where P[subscript i] is an s[subscript i]-to-t[subscript i] path. As a special case of the...
    Resource Type:
    Masters Thesis
    Full Text:
    problem Given graph G and k pairs of terminals {(s1, t1), . . . , (s,, t,)} the Vertex-Disjoint Paths