Sharon Zhou

@realSharonZhou

CS PhD student. Prev. Machine Learning PM. CS & Classics. Working on { evaluation, for medicine, for climate change ☀}

Stanford, CA
sharonzhou.me
Vrijeme pridruživanja: studeni 2016.
20 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @realSharonZhou

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

  1. Prikvačeni tweet
    6. pro 2019.

    HYPE is a Oral!! We evaluate {6️⃣ GANs, 4️⃣ datasets, 2️⃣ sampling methods}. WE show statistically insignificant correlation with FID et al. Fun fact: different GANs excel at different classes in ImageNet, e.g 🍋 vs.📚 Get HYPE

    11 proslijeđenih tweetova 92 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. 22. pro 2019.

    A great venue for submitting work on ML and climate change! :) Also consider signing up for mentorship on your submission! I love seeing research as a collaborative, iterative process of discovery and refinement.

    Submissions for our ICLR workshop "Tackling Climate Change with Machine Learning" are now open! Papers and Proposals due: Feb 4 Apply to mentor or be mentored on submissions: Jan 14 More details:
    3 proslijeđena tweeta 19 korisnika označava da im se sviđa
    Poništi
  3. 9. pro 2019.

    Fun having lunch with two Bayesians and ! ;) w/

    with
    2 proslijeđena tweeta 45 korisnika označava da im se sviđa
    Poništi
  4. 28. stu 2019.

    What Text Editors Fix 💻 Vim: Emacs gave me too many injuries spamming CTRL Emacs: Vim uses the L key to move the cursor Right Nano: I can't get out of Vim or Emacs Sublime Text: Pretty GUIs are more efficient Atom: Sublime keeps asking me to donate

    5 korisnika označava da im se sviđa
    Poništi
  5. 19. stu 2019.

    Glad this is out!! This is also exciting b/c RandAugment makes it easier to incorporate new data augmentation methods ("distortions") than AutoAugment. And, the UDA (Unsupervised Data Augmentation) paper was updated a couple months back to use RandAugment instead of AutoAugment.

    *New paper* RandAugment: a new data augmentation. Better & simpler than AutoAugment. Main idea is to select transformations at random, and tune their magnitude. It achieves 85.0% top-1 on ImageNet. Paper: Code:
    2 proslijeđena tweeta 12 korisnika označava da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    6. stu 2019.

    I've just released a fairly lengthy paper on defining & measuring intelligence, as well as a new AI evaluation dataset, the "Abstraction and Reasoning Corpus". I've been working on this for the past 2 years, on & off. Paper: ARC:

    75 replies 1.255 proslijeđenih tweetova 3.666 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. 6. stu 2019.

    GPT-2's rendition of review comments... Apparently OpenReview is in tweet form?

    5 korisnika označava da im se sviđa
    Poništi
  8. 31. lis 2019.

    Overheard in Silicon Valley 🎃: "I don't want candy. I want money."

    6 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    28. lis 2019.

    MAJOR ANNOUNCEMENT: After working on it for months, I'm so excited the weather and climate landing page has launched! Check out how public weather and climate datasets can support use cases across all industries!

    18 replies 329 proslijeđenih tweetova 942 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. 21. lis 2019.

    "Slow down and look deeper." old Buddhist axiom or new AI paper?

    1 reply 5 proslijeđenih tweetova 27 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    17. lis 2019.

    Could machine learning aid historians in the textual preservation and restoration of inscriptions from ancient Greece? Pythia is the first ancient text restoration model that recovers missing characters from a damaged text input using deep neural networks:

    15 replies 261 proslijeđeni tweet 638 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. 11. lis 2019.

    Training progression of StyleGAN on H&E tissue fragments when a pathologist looks at a biopsy of suspected cancer. 👀💊 40x magnification.

    1 proslijeđeni tweet 5 korisnika označava da im se sviđa
    Poništi
  13. 6. lis 2019.

    Thanks, bot! 🤖

    HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models
    2 korisnika označavaju da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    4. lis 2019.

    Zhou: "Are NMT systems comparable to human translators?" discusses limitations of NMT in this extensive overview:

    1 reply 7 proslijeđenih tweetova 13 korisnika označava da im se sviđa
    Poništi
  15. 24. ruj 2019.

    I bleed my hex codes for you I am not a robot. I am more than that. I too have hex codes, And I bleed them, And I cry them, Breaking composure In regularity In convexity From polygon recurrence. - A GAN that I have been working on inspired by

    13 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    20. ruj 2019.

    Had a lot of fun presenting recent work in point-of-care medical imaging and strategies to scale worldwide at Plus.... upgraded cartoons 😆 Check it out:

    16 proslijeđenih tweetova 42 korisnika označavaju da im se sviđa
    Poništi
  17. 19. ruj 2019.

    The architect Gaudí was a human GAN.

    1 reply 1 proslijeđeni tweet 11 korisnika označava da im se sviđa
    Poništi
  18. 21. kol 2019.

    has been on fire for the past 3 weeks. Looking around, I found as the most direct way to aid the indigenous Brazilian inhabitants fighting the flames, on the ground now.

    1 reply 2 proslijeđena tweeta 3 korisnika označavaju da im se sviđa
    Poništi
  19. 8. kol 2019.

    Climate actions ranked! 1, 6, and 7 will probably surprise you.

    3 korisnika označavaju da im se sviđa
    Poništi
  20. 31. srp 2019.

    Excited to announce the 2nd annual WeCNLP Summit! Together with steering committee and among others, this summit will convene NLP researchers in academia and industry for talks, panel, and posters. Register now: Sept 6 at Facebook HQ.

    1 proslijeđeni tweet 5 korisnika označava da im se sviđa
    Poništi

@realSharonZhou 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:

    ·