Search Constraints

Start Over
Filtering by: Creator Svesko, Andrew M. Remove constraint Creator: Svesko, Andrew M. Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • Mental Models of Mere Mortals with Explanations of Reinforcement Learning

    Creator:
    Anderson, Andrew A.
    Abstract:
    How should reinforcement learning (RL) agents explain themselves to humans not trained in AI? To gain insights into this question, we conducted a 124 participant, four-treatment experiment to compare participants’ mental models of an RL agent in the context of a simple Real-Time Strategy (RTS) game. The four treatments isolated...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Andrew A. Anderson for the

  • A Benchmarking Study of Unsupervised Anomaly Detection Algorithms

    Creator:
    Emmott, Andrew F.
    Abstract:
    It is common practice in the unsupervised anomaly detection literature to create experimental benchmarks by sampling from existing supervised learning datasets. We seek to improve this practice by identifying four dimensions important to real-world anomaly detection applications --- point difficulty, clusteredness of anomalies, relevance of features, and relative frequency of...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Andrew Emmott for the

  • High-performance data-parallel input/output

    Creator:
    Moore, Jason Andrew
    Abstract:
    Existing parallel file systems are proving inadequate in two important arenas: programmability and performance. Both of these inadequacies can largely be traced to the fact that nearly all parallel file systems evolved from Unix and rely on a Unix-oriented, single-stream, block-at-a-time approach to file I/O. This one-size-fits-all approach to parallel...
    Resource Type:
    Dissertation
    Full Text:
    Jason A. Moore presented on July 19, 1996 APPROVED: M jor Professor, representing Computer Science

  • MARLA : a chess playing program

    Creator:
    Rood, Andrew Lloyd
    Abstract:
    MARLA is a collection of FORTRAN routines which implements the Shannon-type-chess program with alphabeta cutoffs occurring dynamically. Board positions are updated incrementally. Also involved in position analysis is a production system which models the human chess player's advice-taking, theme, and chess learning in a general sense. Interfacing these two sections,...
    Resource Type:
    Masters Thesis
    Full Text:
    . MARLA: A Chess Playing Program by Andrew Lloyd Rood A THESIS submitted to Oregon State University

  • New Strategies to Develop Hidden Markov Models Combining KEGG and Pfam

    Creator:
    Gupta, Sonica
    Abstract:
    Profile Hidden Markov Models utilize the information stored in a multiple sequence alignment such as its residues and conserved regions to assign probabilities at each column. This indicates areas in the sequences where similar functionality is observed. These probability weights are then combined to assign a sequence score, which is...
    Resource Type:
    Honors College Thesis
    Full Text:
    _____________________________________________________________________ Andrew Thurber, Committee Member, representing Department of Microbiology

  • Learning classification rules by randomized iterative local search

    Creator:
    Chisholm, Michael (Michael Andrew), 1974-
    Abstract:
    Learning easily understandable decision rules from examples is one of the classic problems in machine learning. Most learning algorithms for this problem employ some variation of a greedy separate-and-conquer algorithm. In this paper, we describe a system called LERILS that learns highly accurate and comprehensible rules from examples using a...
    Resource Type:
    Masters Thesis
    Full Text:
    this would slow the algorithm down. M needs to be large enough that there are good variety of

  • How does AAR/AI Support Problem Solvers with Diverse Behaviors and Cognitive Styles?

    Creator:
    Dikkala, Rupika
    Abstract:
    "What’s wrong with this AI?" Explainable AI (XAI) researchers are moving beyond explaining an AI’s actions, to helping users detect an AI’s failures. However this detection may not be enough—for actionability, we often need to pinpoint which part failed. We investigate how AAR/AI, a structured assessment process, supports users with...
    Resource Type:
    Masters Thesis
    Full Text:
    : Margaret M. Burnett “What’s wrong with this AI?” Explainable AI (XAI) researchers are moving beyond ex

  • 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

  • Practices for Engineering Gender-Inclusivity into Software

    Creator:
    Hilderbrand, Claudia
    Abstract:
    Although the need for gender-inclusivity in software itself is gaining attention among both SE researchers and SE practitioners, and methods have been published to help, little has been reported on how to make such methods work in real-world settings. For example, how do busy software practitioners use such methods in...
    Resource Type:
    Masters Thesis
    Full Text:
    reports for staff L 7 technologies M 2 Education platform for instructors N >12 An IT-support

  • The expressive power and declarative attributes of exception handling in Forms/3

    Creator:
    Agrawal, Anurag
    Abstract:
    Exception handling is a programming language feature that can help increase the reliability of programs. However, not much work has been done on exception handling in visual programming languages. We present an approach for improving the exception handling mechanism in Forms/3, a declarative visual programming language based on the spreadsheet...
    Resource Type:
    Masters Thesis
    Full Text:
    Declarative Attributes of Exception Handling in Forms/3. Abstract approved: Mafgaret M. Burnett Exception