Данил Бухвалов (brother2) wrote,
Данил Бухвалов

вдруг кому пригодится

In summary, we have studied the robustness of machine
learning approaches in classifying different phases of matter.
Our discussion is mainly focused on supervised learning
based on deep neural networks, but its generalization to other
types of learning models (such as unsupervised learning or
support vector machines) and other type of phases are possible
and straightforward. Through two concrete examples,
we have demonstrated explicitly that typical phase classifiers
based on deep neural networks are extremely vulnerable to
adversarial examples. Adding a tiny amount of carefully
crafted noises or even just changing a single pixel may cause
the classifier to make erroneous predictions at a surprisingly
high confidence level. In addition, through adversarial training,
we have shown that the robustness of phase classifiers to
specific types of adversarial perturbations can be significantly
improved. Our results reveal a novel vulnerability aspect for
the growing field of machine learning phases of matter, which
would benefit future studies across condensed matter physics,
machine learning, and artificial intelligence.
Tags: arxiv.org

  • Post a new comment


    default userpic

    Your reply will be screened

    When you submit the form an invisible reCAPTCHA check will be performed.
    You must follow the Privacy Policy and Google Terms of use.