Pierre Gutierrez

@prrgutierrez

Formerly Data Scientist . Now machine learning researcher at

Vrijeme pridruživanja: prosinac 2009.

Tweetovi

Blokirali ste korisnika/cu @prrgutierrez

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

  1. proslijedio/la je Tweet
    31. sij

    A well done video explanation of FixMatch, thanks !

    Poništi
  2. proslijedio/la je Tweet
    30. sij

    One of the best decisions we ever made Applied Deep Learning Research was to standardize on for all our research. It has made us more productive and made our work more fun. Glad to see agrees!

    Poništi
  3. 30. sij

    Great video on RandAugment by on his Henry AI Labs channel!

    Poništi
  4. proslijedio/la je Tweet
    28. sij

    Q: Can deterministic (AEs) learn latent spaces that are as smooth and meaningful as do? A: Yes, see gif and read small thread 👇 👇 👇 Work with Mehdi M.S. Sajjadi accepted at 👇 1/

    Prikaži ovu nit
    Poništi
  5. 27. sij
    Poništi
  6. proslijedio/la je Tweet
    22. sij
    Odgovor korisnicima

    Meanwhile, Google funds ITIF, a tech 'think tank' which is fighting a ban in Portland and other potential restrictions on facial recognition.

    Poništi
  7. proslijedio/la je Tweet

    In the last two days, Google and editorial board have called for a temporary moratorium on facial recognition - following in the footsteps of many researchers and civil society orgs.

    Poništi
  8. 22. sij

    I loved the original paper (and not just because of the title)

    Prikaži ovu nit
    Poništi
  9. 22. sij

    Interesting to see that antialiasing layers are now part of state of the art architecture!

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    22. sij

    FixMatch: focusing on simplicity for semi-supervised learning and improving state of the art (CIFAR 94.9% with 250 labels, 88.6% with 40). Collaboration with Kihyuk Sohn, Nicholas Carlini

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    20. sij

    Our paper "Overly Optimistic Prediction Results on Imbalanced Data: Flaws and Benefits of Applying Over-sampling" has been published on arXiv: What did we do? A thread... (1/6)

    Prikaži ovu nit
    Poništi
  12. 20. sij
    Poništi
  13. proslijedio/la je Tweet
    18. sij
    Poništi
  14. 19. sij
    Poništi
  15. proslijedio/la je Tweet
    18. sij

    Many stories on tech can be overblown. Not this one though I have seen this app in use and it 100% works and is even more disconcerting than description here Global facial recognition doesn’t exist only because of social norms rn. The tech is trivial

    Poništi
  16. 16. sij
    Poništi
  17. proslijedio/la je Tweet
    14. sij

    been hacking for awhile on the idea of training an embedding based YOLO with self supervision contrastive loss. have never had a good solution for unsupervised object detection piece.... until now!!! "Contrastive Learning of Structured World Models"

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    14. sij

    At medical imaging we often need to make a little data go a long way. One under-appreciated approach for this is self-supervised learning. It's almost magical! I've written a little overview to help you get started. Let me know if you try it :)

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    10. sij

    Par exemple, prenons une jolie configuration à... 4 corps désormais ! Regardez les premiers tours, c'est joli hein... Ouais continuez à regarder... CA VA MAL FINIR !

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    11. sij

    “Meet AdaMod: a new deep learning optimizer with memory” by Less Wright

    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:

    ·