Live data from Hacker News

Viewing profile — derivt

derivt

HN member
Joined
Sat, Feb 24, 2018, 10:49 AM UTC
HN karma
3
Public activity
12 items

About derivt

No profile information was provided.

Recent public activity

  1. comment
    Comment #16504611

    Sorry, I am not a native English speaker, but I think it should be White Asian, do you say white americans? Also, Google accused in lawsuit of excluding white and Asian men in hiri…

  2. comment
    Comment #16504459

    Higher education is not overestimated if it gives you better opportunities for the future. Perhaps some kind of higher education provides little economic value. I think that from a…

  3. comment
    Comment #16504405

    Why collage and not college? https://www.learnenglish.de/mistakes/collagevscollege.html

  4. comment
    Comment #16504392

    Why is American capitalized and asian isn't?

  5. comment
    Comment #16500415

    When you are designing an hypothesis test the term positive and negative are not so clear. For example you can test that mean weight of bags is greater than 5.0 kg or smaller than …

  6. comment
    Comment #16482501

    The experiment you suggest seems promising. As a math teacher, I don't know about this field. But to suggest experiments that "could" prove or support and hypothesis is a good way …

  7. comment
    Comment #16482209

    Don't know anything about RNA, but I wonder if some kind of small virus could be used to test the micro RNA transport hypothesis. Googling "micro RNA virus", first link is https://…

  8. comment
    Comment #16452871

    This kind of attack relies on a low margin DNN, see (1), a low spectral norm of the input-output jacobian matrix guarantees good generalization error. So a one pixel attack exploit…

  9. comment
    Comment #16452816

    Given that DNN are deep, what a one pixel attack means is that one pixel change propagates through the map of features: one pixel => 0-level-feature change -> one 1-level feature c…

  10. comment
    Comment #16452784

    If in a DNN for label a cat we explore the group of movements of the animal cat (realistic movements available for a cat) we could relate the discriminative power of the DNN to the…

  11. comment
    Comment #16452765

    this paper https://openreview.net/forum?id=HJC2SzZCW suggest that sensivity is related to poor generalization power. To define derivative we need to use a natural parameter in such…

  12. comment
    Comment #16452723

    We need to define the derivative of a deep model. I mean a way to measure how a model change when we change one pixel in the training data. Since pixel -> feature -> margin, we nee…