Kevin Swersky

@kswersk

Research Scientist at Google Brain in Toronto. Interested in all things machine learning and AI.

Vrijeme pridruživanja: lipanj 2015.

Tweetovi

Blokirali ste korisnika/cu @kswersk

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

  1. 14. pro 2019.
    Prikaži ovu nit
    Poništi
  2. 14. pro 2019.
    Prikaži ovu nit
    Poništi
  3. 14. pro 2019.
    Prikaži ovu nit
    Poništi
  4. 14. pro 2019.
    Prikaži ovu nit
    Poništi
  5. 14. pro 2019.

    Morning sessions (already happened): Morning: 

    Prikaži ovu nit
    Poništi
  6. 14. pro 2019.

    We are live-streaming the ML for systems workshop. Next session is the contributed talks. Below are the links for people who wish to watch remotely.

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    14. pro 2019.

    Shining light on how to get live experiments right at Facebook. “Making multi-objective optimization to be compatible with human decision-making (esp at big organizations) is hard” It’s never a pure optimization problem in practice.

    Poništi
  8. proslijedio/la je Tweet
    14. pro 2019.

    I'm looking forward to giving a talk on Saturday from 1:45-2:15 PM at the Workshop on Machine Learning for Systems. I'll be talking about some work we're doing in this area at , including RL for ASIC chip design & (cont)

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    11. pro 2019.
    Odgovor korisnicima i sljedećem broju korisnika:

    Code is now available!

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

    Classifiers are secretly energy-based models! Every softmax giving p(c|x) has an unused degree of freedom, which we use to compute the input density p(x). This makes classifiers into generative models without changing the architecture.

    , , i još njih 2
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    8. pro 2019.

    Excited for the tutorial tomorrow (Dec 9) at 9am at If you are at the conference and would to chat, please send me an email (also, if you are interested in a post-doc position in our group at Tokyo).

    Poništi
  12. 8. pro 2019.

    My journey into machine learning research began with energy based models (RBMs). It’s been fun revisiting them! They can be quite powerful if trained well.

    Poništi
  13. proslijedio/la je Tweet
    7. stu 2019.

    An update: has been in contact with Canadian immigration officials. They told him that anyone who has been denied a visa to attend can request their case to be reconsidered via this form:   No guarantees, but please pass along!

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet

    I ask students and new authors of to not take reviews to heart. If you believe in your work, you have to keep fighting for it. Try to read objectively and decide which comments are constructive. Don't let reviewers determine your self worth. You deserve to be here!

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    4. stu 2019.

    Looking forward to many wonderful talks at the Conference on Data Science at Fields institute that I am co-organizing in Toronto from Nov 12-15. See full list of speakers here

    Poništi
  16. proslijedio/la je Tweet
    2. stu 2019.

    Meta-Dataset: a new benchmark for training and evaluating models that is large-scale, consists of diverse datasets, and presents more realistic tasks by

    Poništi
  17. proslijedio/la je Tweet
    24. lis 2019.

    Our research team is using graph neural networks to predict the olfactory properties of molecules, expanding our understanding of smell & odor, with potential applications ranging from odorant synthesis to scent digitization. Learn more at

    Poništi
  18. proslijedio/la je Tweet
    25. ruj 2019.

    Thank you Machine Learning community for getting off to such a great start 🎉. Congratulations to everyone who submitted and for pushing our science to new heights 📈. Read the papers: 2594 now online Next phase: Bidding, instructions on Friday.

    Poništi
  19. proslijedio/la je Tweet
    16. ruj 2019.

    deadlines posted: Abstracts due: Jan 30 Papers due: Feb 6 Reviews out: Mar 31 Response due: Apr 7 Notifications: May 8 Conference: Jul 11-17 We aimed 8+ weeks notification->conference to decrease the number who cannot attend for Visa reasons.

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

    Happy to announce 'ML for Systems' workshop is accepted to w/ , , , M. Hashemi, . Looking forward to your papers (CFP ) & invited talks (TBA). See the website for previous edition's accepted papers :)

    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:

    ·