Search Constraints

Start Over
Filtering by: Creator Thomas, Gerald Evan Remove constraint Creator: Thomas, Gerald Evan Academic Affiliation Electrical Engineering and Computer Science Remove constraint Academic Affiliation: Electrical Engineering and Computer Science

Search Results

  • 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

  • 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

  • CAM : a new Circuit Augmentation Method for modeling interconnects and passive components

    Creator:
    Kolstad, Joel W.
    Abstract:
    Contemporary circuit design involves significant computer-based simulation, calling for a balance between circuit model accuracy and simulation run time. Traditionally, circuit modelers concentrated on producing either (1) physically-based models, where each element in the model correlates to a physically meaningful aspect of the device being modeled or (2) mathematically-based "macromodels,"...
    Resource Type:
    Masters Thesis
    Full Text:
    to Dr. Karti Mayaram, Dr. Thomas Plant, and my GCR Dr. Kagan Tumer for taking the time to review

  • 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

  • Cryptanalysis and enhancement of authentication protocols

    Creator:
    Kim, Minho
    Abstract:
    Authentication protocols play important roles in network security. A variety of authentication protocols ranging from complex public-key cryptosystems to simple password-based authentication schemes have been proposed. However, currently there is no fully secure authentication scheme that can resist all known attacks. When a user authentication is performed over an insecure...
    Resource Type:
    Dissertation
    Full Text:
    teaching. I also want to extend great appreciation to Professor Zhongfeng Wang, Traylor Roger, Thomas

  • Communication-Efficient Secure Two-Party Computation From Minicrypt and OT

    Creator:
    Roy, Lawrence
    Abstract:
    Secure two-party computation (2PC) is the task of performing arbitrary calculations on secret inputs provided by two parties, while maintaining secrecy if at least one party is honest. 2PC has been applied to privacy-preserving record linkage and machine learning, in areas such as medicine where maintaining privacy is crucial. One...
    Resource Type:
    Dissertation