Search Constraints

Start Over
Filtering by: Creator Pearcy, Bill Remove constraint Creator: Pearcy, Bill Creator Kulesza, Todd Remove constraint Creator: Kulesza, Todd Non-Academic Affiliation Oregon State University. Graduate School Remove constraint Non-Academic Affiliation: Oregon State University. Graduate School

Search Results

  • Toward end-user debugging of machine-learned programs

    Creator:
    Kulesza, Todd
    Abstract:
    The results of a machine learning from user behavior can be thought of as a program, and like all programs, it may need to be debugged. Providing ways for the user to debug it matters because without the ability to fix errors, users may find that the learned program’s errors...
    Resource Type:
    Masters Thesis
    Full Text:
    university life, Bill and Iris McCanless’ cafe has become a home away from home; most of these words were

  • Personalizing machine learning systems with explanatory debugging

    Creator:
    Kulesza, Todd
    Abstract:
    How can end users efficiently influence the predictions that machine learning systems make on their behalf? Traditional systems rely on users to provide examples of how they want the learning system to behave, but this is not always practical for the user, nor efficient for the learning system. This dissertation...
    Resource Type:
    Dissertation
    Full Text:
    without the support of family and friends. I’d particularly like to acknowledge Bill and Iris McCanless