Search Constraints

Start Over
Filtering by: Creator Mulligan, Daniel M. Remove constraint Creator: Mulligan, Daniel M. Committee Member Fern, Alan Remove constraint Committee Member: Fern, Alan Contributor Bremer, Peer Timo Remove constraint Contributor: Bremer, Peer Timo

Search Results

  • 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:
    vs. StyleGAN-R. And CelebA-M is a control dataset we create that does not contain glasses, ties and