Search Constraints

Start Over
Filtering by: Creator DeDen, F. Michael Remove constraint Creator: DeDen, F. Michael Contributor Li, Fuxin Remove constraint Contributor: Li, Fuxin Contributor Bremer, Peer Timo Remove constraint Contributor: Bremer, Peer Timo License All rights reserved Remove constraint License: All rights reserved

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:
    . . . . . . . . . . . . . . . . . . 75 4.3 A diagram of our xGA model. G𝑟 , G𝑐, and F are fixed pretrained models. 𝛿𝑛 and 𝛿𝑛 are