Distill

@distillpub

Supporting Clarity in Machine Learning

San Francisco
distill.pub
Vrijeme pridruživanja: listopad 2016.
6 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @distillpub

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @distillpub

  1. proslijedio/la je Tweet
    28. sij

    1/2 Last year I wrote an article with . Distill represents a promising new paradigm in academic publishing. I wrote a blog post about my Distill experience:

    18 proslijeđenih tweetova 99 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. 15. sij

    Visualizing the Impact of Feature Attribution Baselines -- A new Distill article by Pascal Sturmfels, Scott Lundberg, and Su-In Lee.

    55 proslijeđenih tweetova 183 korisnika označavaju da im se sviđa
    Poništi
  3. 4. stu 2019.

    ... and their accompanying open source library:

    16 proslijeđenih tweetova 34 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. 4. stu 2019.

    Computing Receptive Fields of Convolutional Neural Networks -- A new Distill article by André Araujo, Wade Norris, and Jack Sim.

    105 proslijeđenih tweetova 359 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. 30. ruj 2019.

    The Paths Perspective on Value Learning — A new Distill article by and .

    1 reply 70 proslijeđenih tweetova 226 korisnika označava da im se sviđa
    Poništi
  6. 8. kol 2019.

    Distill was excited to try using 's relations metadata to register connections between different documents in our "discussion article" experiment. Example: It's cool that modern academic publishing infrastructure supports this!

    6 proslijeđenih tweetova 23 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    6. kol 2019.

    Anybody studying adversarial examples should read this document. It is not just a good read, but an interesting new format for serious scientific discourse.

    A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' - Six comments from the community and responses from the original authors.
    Prikaži ovu nit
    26 proslijeđenih tweetova 151 korisnik označava da mu se sviđa
    Poništi
  8. proslijedio/la je Tweet
    6. kol 2019.

    Really cool directions and thinking on adversarial examples. I really wish this kind of concerted conversation could happen more. This is how we make scientific progress.

    A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' - Six comments from the community and responses from the original authors.
    Prikaži ovu nit
    2 proslijeđena tweeta 13 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    6. kol 2019.

    This is a brilliant way to do post publication review.

    A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' - Six comments from the community and responses from the original authors.
    Prikaži ovu nit
    1 reply 2 proslijeđena tweeta 14 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    6. kol 2019.

    The folks at continue to blaze the trail in every possible respect, showing what the future of publishing should look like.

    In helping organize this article, I was really blown away by the amount of work some respondents put in. In some cases, people literally spent weeks thinking and doing experiments to clarify the original paper. Contrast with peer review where spending a few hours is a lot.
    4 proslijeđena tweeta 38 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    6. kol 2019.

    Strongly recommended readings. Not only a milestone to the understanding of the robustness problem, but also milestone on research collaboration, transparency, open criticism and open science.

    A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' - Six comments from the community and responses from the original authors.
    Prikaži ovu nit
    2 proslijeđena tweeta 15 korisnika označava da im se sviđa
    Poništi
  12. 6. kol 2019.

    We'd love community feedback on our "discussion article" experiment! Should we run more? Anything we could have done better? Any topics we should consider?

    A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' - Six comments from the community and responses from the original authors.
    Prikaži ovu nit
    11 proslijeđenih tweetova 43 korisnika označavaju da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    6. kol 2019.

    A lot of issues w/ the peer review process are (IMO) incentive issues. Making cite-able artifacts out of short responses to published seems like good incentive design.

    7 proslijeđenih tweetova 32 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    6. kol 2019.

    I'm very excited about this type of article. It feels like formally recognizing that the hard work of peer review is a research contribution as well: we saw both the original authors and respondents invest considerable effort replicating results and running new experiments.

    A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' - Six comments from the community and responses from the original authors.
    Prikaži ovu nit
    1 reply 14 proslijeđenih tweetova 75 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    6. kol 2019.

    This is new 'peer commentary' format that Distill is experimenting with is awesome. I wanted to set something like this up over a year ago, inspired by . Unlike me et al actually made it happen. Very well executed, too! Thank you and I hope it will catch on!

    A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' - Six comments from the community and responses from the original authors.
    Prikaži ovu nit
    24 proslijeđena tweeta 98 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    6. kol 2019.

    At a meta-level, this sort of discussion article is a really great idea and I hope it catches on. I also think the specific analyses in this collection are really compelling.

    A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' - Six comments from the community and responses from the original authors.
    Prikaži ovu nit
    1 reply 7 proslijeđenih tweetova 26 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. 6. kol 2019.

    With comments from , , , , , & and discussion from the original authors , , , , Brandon Tran, & .

    2 proslijeđena tweeta 28 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. 6. kol 2019.

    A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' - Six comments from the community and responses from the original authors.

    6 replies 218 proslijeđenih tweetova 673 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. 9. tra 2019.

    Open Questions about Generative Adversarial Networks — A new Distill article by .

    52 proslijeđena tweeta 143 korisnika označavaju da im se sviđa
    Poništi
  20. 2. tra 2019.

    A Visual Exploration of Gaussian Processes — A new Distill article by , Rebecca Kehlbeck, and

    176 proslijeđenih tweetova 562 korisnika označavaju da im se sviđa
    Poništi

@distillpub još nije objavio nijedan Tweet.

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·