Ben Recht

@beenwrekt

optimization. machine learning. uc berkeley. i don't know why twitter thinks you want to see my likes.

Vrijeme pridruživanja: kolovoz 2011.

Tweetovi

Blokirali ste korisnika/cu @beenwrekt

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

  1. Prikvačeni tweet
    8. stu 2017.

    the first step is admitting you have a problem

    Poništi
  2. 4. pro 2019.

    By popular demand, we've extended the L4DC submission deadline until December 20. Enjoy the learning and control conferences between now and then!

    Poništi
  3. 2. pro 2019.

    Reminder that submissions for L4DC 2020 are due this Friday! Any exciting results bridging machine learning, dynamics, and control are welcome and encouraged. More info here:

    Poništi
  4. 11. stu 2019.

    ICYMI: Reminder that submissions for L4DC 2020 are now open. Deadline is December 6. We’re excited to read your contributions!

    Poništi
  5. 16. lis 2019.

    The strangest misconception of the current deepRL craze is that sim2real is hard.

    Poništi
  6. 14. lis 2019.

    Seems troubling: Many of the images in the CXR-14 chest x-ray data set are post treatment and have chest drains in the images. Once these examples are removed, machine learning performs worse than a first year resident. h/t

    Poništi
  7. 8. lis 2019.

    Unreasonably excited by the package I received today! I never get anything good in my work mailbox. So cool that this book is out.

    Poništi
  8. proslijedio/la je Tweet
    8. lis 2019.

    Stich Fix is selling something called pants, a concept from quantum mechanics.

    Poništi
  9. 1. lis 2019.

    4 years ago today, called out the perils of big data in a keynote at . Worth taking 20 mins to see how prescient he was and how much work is left to do.

    Poništi
  10. proslijedio/la je Tweet
    9. ruj 2019.

    We're excited to release a draft of the causality chapter at . There's been lots of interest in the topic and we hope the chapter is a helpful introduction.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    8. ruj 2019.

    To better know Media Lab history & context, check out smart & careful work of these 2 women (who I also proudly call friends): on roots of ML money on ML design & development ideologies; “Charisma Machine”

    Poništi
  12. 4. ruj 2019.

    Thanks to for teaching me how to pronounce name of the AI conference we have in Winter.

    Poništi
  13. 27. kol 2019.

    Michael Hiltzik pulls no punches about MIT’s embarrassing Koch problem:

    Poništi
  14. 25. kol 2019.

    It’s infuriating to compare MIT’s plea for forgiveness for taking $800K from Epstein to its fawning, whitewashing eulogy of David Koch who gave them hundreds of millions. These were posted a day apart from each other:

    Poništi
  15. 22. srp 2019.

    Remember when OpenAI invented the ResNet? Neither do I, because it was developed at Microsoft Research.

    Poništi
  16. 7. lip 2019.

    And awesome to see many Berkeley alums thriving here. , , and Shivaram Venkataraman.

    Poništi
  17. 7. lip 2019.

    Was amazing to catch up with my great Madison colleagues, , , Rob Nowak, , . Though sad to miss who was building human pyramids in Germany.

    Poništi
  18. 7. lip 2019.
    Prikaži ovu nit
    Poništi
  19. 7. lip 2019.

    Surprisingly, detection algorithms were just as vulnerable as classification algorithms to subtle changes in view. The fox becomes a sheep, the airplane becomes a horse, the motorcycle becomes a lizard. All examples occur within 10 frames of each other in the video. (3/4)

    Prikaži ovu nit
    Poništi
  20. 7. lip 2019.

    This work follows up on inspirational work by Azulay and Weiss () and Gu et al. () which highlighted the variability of image classifiers over videos. (2/4)

    Prikaži ovu nit
    Poništi
  21. 7. lip 2019.

    Today’s talk features, in particular, some great work by , Achal Dave, , and systematically breaking image classifiers using video. Code, paper, and data are here: (1/4)

    Prikaži ovu nit
    Poništi

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:

    ·