Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations

    Anirudh Goyal
    Anirudh Goyal
    Dmitriy Serdyuk
    Dmitriy Serdyuk
    Sandeep Subramanian
    Sandeep Subramanian

    arXiv: Machine Learning, Volume abs/1804.02485, 2018.

    Cited by: 6|Bibtex|Views56|Links
    EI

    Abstract:

    Deep networks have achieved impressive results across a variety of important tasks. However a known weakness is a failure to perform well when evaluated on data which differ from the training distribution, even if these differences are very small, as is the case with adversarial examples. We propose Fortified Networks, a simple transforma...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments