Search Constraints

Start Over
Filtering by: Creator Thomas, Gerald Evan Remove constraint Creator: Thomas, Gerald Evan Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • AI, Robot: A Rhetorical Analysis of Jeopardy! Matches Featuring IBM’s Artificial Intelligence

    Creator:
    Steele, Evan T.
    Abstract:
    The relationship between the public and new technologies has historically been a tumultuous one, with public perceptions ranging from excited rapid adoption to standoffish pessimism. In 2011, IBM tried to use competition as a means of showcasing a new technology to the public. This thesis is a work of rhetorical...
    Resource Type:
    Masters Thesis
    Full Text:
    ABSTRACT OF THE THESIS OF Evan T. Steele, for the degree of Master of Arts in Interdisciplinary Studies

  • Explanations and Processes to Enable Humans to Assess AI with Respect to Manipulable Properties

    Creator:
    Dodge, Jonathan E.
    Abstract:
    Assessing AI systems is difficult. Humans rely on AI systems in increasing ways, both visible and invisible, meaning a variety of stakeholders need a variety of assessment tools (e.g., a professional auditor, a developer, and an end user all have different needs). We posit that it is possible to provide...
    Resource Type:
    Dissertation
    Full Text:
    , Zhengxian Lin, Theresa Mai, Sai Raja, Caleb Matthews, Nicholas Kiddle, Evan Newman, Christopher Perdriau

  • Active learning with committees : an approach to efficient learning in text categorization using linear threshold algorithms

    Creator:
    Liere, Ray
    Abstract:
    We developed and investigated machine learning methods that require minimal preprocessing of the input data, use few training examples, run fast, and still obtain high levels of accuracy. Most approaches to designing machine learning programs are based on the supervised learning paradigm – training examples are chosen randomly and given...
    Resource Type:
    Dissertation
    Full Text:
    . Gerald Smith, and Prof. Robert Kiekel. All have shown special patience as I requested permission to do

  • Classification context in a machine learning approach to predicting protein secondary structure

    Creator:
    Langford, Bill T.
    Abstract:
    An important problem in molecular biology is to predict the secondary structure of proteins from their primary structure. The primary structure of a protein is the sequence of amino acid residues. The secondary structure is an abstract description of the shape of the folded protein, with regions identified as alpha...
    Resource Type:
    Masters Thesis
    Full Text:
    Machine Learning Approach to Predicting Protein Secondary Structure Abstract approved. Thomas G

  • A probabilistic model for anomaly detection in remote sensor streams

    Creator:
    Dereszynski, Ethan W.
    Abstract:
    Remote sensors are becoming the standard for observing and recording ecological data in the field. Such sensors can record data at fine temporal resolutions, and they can operate under extreme conditions prohibitive to human access. Unfortunately, sensor data streams exhibit many kinds of errors ranging from corrupt communications to partial...
    Resource Type:
    Masters Thesis
    Full Text:
    Remote Sensor Streams Abstract approved: Thomas G. Dietterich Remote sensors are becoming the standard

  • Learning and Improving Policies for Probabilistic Planning Problems

    Creator:
    Issakkimuthu, Murugeswari
    Abstract:
    In this work, we study the problem of learning and improving policies for probabilistic planning problems. In the first part, we train neural network policies for probabilistic planning problems modeled as factored Markov decision problems. The objective is to train problem-specific neural networks via supervised learning to imitate the action...
    Resource Type:
    Dissertation
    Full Text:
    learning experience I have had as his student, and my Ph.D. committee members, Prof. Thomas Dietterich

  • Individual Fairness Optimization in Machine Learning with Minimax Loss and an Abstain Option

    Creator:
    Behnoudfar, Ali
    Abstract:
    In this thesis, a new learning algorithm is introduced that is targeted towards individual fairness. In order to be individually fair, mispredictions need to be avoided as each such prediction means the learning algorithm was unfair towards some individual. Therefore, achieving individual fairness implies having a perfect classifier, which is...
    Resource Type:
    Masters Thesis

  • Analytical Methods for Improving Causal Inference

    Creator:
    Sinha, Meghamala
    Abstract:
    Causal inference is an important analytical tool to bridge the gap between prediction and decision-making. However, learning a causal network solely from data is a challenging task. In this work, various techniques have been explored for a better and improved causal network learning from data. Firstly, the problem of learning...
    Resource Type:
    Dissertation
    Full Text:
    Tadepalli, Dr. Rebecca Hutchinson, and Dr. Thomas Sharpton, for their insightful comments and encouragement

  • Species Distribution Modeling of Citizen Science Data as A Classification Problem with Class-Conditional Label Noise

    Creator:
    He, Liqiang
    Abstract:
    Species distribution models (SDM), which quantify the correlation between the distribution of a species and environmental factors, are increasingly used to map and monitor animal and plant distributions in the context of awareness of environmental change and its ecological consequence. For perfect data, this is a straightforward classification problem from...
    Resource Type:
    Masters Thesis
    Full Text:
    thank my thesis committee: Prof. Thomas G. Dietterish, Prof. Amir Nayyeri and Prof. John P. Bolte, for

  • Fine-Grained Object Recognition Under Limited Training Data

    Creator:
    Lam, Michael Q.
    Abstract:
    This dissertation addresses object recognition in challenging settings, where distinct object classes are visually very similar (e.g., species of birds and insects) and/or access to training examples of object classes is limited (e.g., due to the associated high costs of data annotation). In this dissertation, we present a variety of...
    Resource Type:
    Dissertation
    Full Text:
    also like to thank my former co-advisor Thomas Dietterich for his guidance on my early research. I am