Han Zhang

@Han_Zhang_

Research Scientist at Google Brain

Vrijeme pridruživanja: rujan 2012.

Tweetovi

Blokirali ste korisnika/cu @Han_Zhang_

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

  1. Prikvačeni tweet
    28. lis 2019.

    Thanks Augustus! Enjoy working with you on GANs again :)

    Poništi
  2. proslijedio/la je Tweet
    prije 8 sati
    Poništi
  3. 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
  4. proslijedio/la je Tweet
    27. stu 2019.

    New paper: Your Local GAN: a new layer of two-dimensional sparse attention and a new generative model. Also progress on inverting GANs which may be useful for inverse problems. with from NTUA and from

    Poništi
  5. proslijedio/la je Tweet
    30. lis 2019.

    Is your GAN too big? Try Small-GAN! : w/ @sam_sinha_, , , Yoshua Bengio, , and me. We use Coreset-sampling to build small batches that `mimic' large batches. 1/6

    Prikaži ovu nit
    Poništi
  6. 23. svi 2018.

    Fantastic internship experience with . Hope to work with you guys again in the near future.

    Poništi
  7. proslijedio/la je Tweet
    Poništi
  8. proslijedio/la je Tweet

    Another nice post in Distill on techniques for avoiding checker artifacts during upsampling ops TLDR: nn-resize conv

    Poništi
  9. proslijedio/la je Tweet
    14. lis 2016.

    Check out an interactive article on how to effectively use and interpret t-SNE visualizations -

    Poništi
  10. proslijedio/la je Tweet
    15. srp 2016.
    Poništi
  11. proslijedio/la je Tweet

    Read Google Brain WikiReading paper (); nice read, took some notes, might as well post them:

    Poništi
  12. proslijedio/la je Tweet

    The new WikiReading dataset looks impressive …: 18M text reading comprehension instances across ~50% of wikipedia.

    Poništi
  13. 9. kol 2016.
    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:

    ·