1. 6
    ThisIs_MyName avatar ThisIs_MyName 9 months ago | link | on: Fooling Neural Networks in the Physical World with 3D Adversarial Objects

    This is incredible! Is the code open source?

    1. 13
      loganengstrom avatar loganengstrom 9 months ago | link

      Not yet, but it will be soon!

      1. 3
        Lanny avatar Lanny 9 months ago | link

        It doesn’t look like it but there is a draft of the paper available: https://arxiv.org/pdf/1707.07397.pdf

        1. 2
          k749gtnc9l3w avatar k749gtnc9l3w 9 months ago | link

          They have a «code» link that says «coming soon» — so, not yet, but hopefully it will be in the future.

        1. 2
          loganengstrom avatar loganengstrom 2 years ago | link | on: Mathematicians are chronically lost and confused (and that's how it's supposed to be)

          I think it really depends on the subject you’re learning. If you’re learning some sort of theoretical domain, such as analysis, you certainly have to work through every theorem - otherwise you won’t really understand the course of the subject. On the other hand if you’re learning applied calculus or linear algebra working through every theorem probably isn’t as great - by the nature of the class you’re already skipping over tons of theoretical details. I don’t like the black and white tone of this article.