(((λ()(λ() 'yoav))))

@yoavgo

Israel
cs.biu.ac.il/~yogo/
Joined May 2009
474 Photos and videos Photos and videos

Tweets

@yoavgo is blocked

Are you sure you want to view these Tweets? Viewing Tweets won't unblock @yoavgo.

  1. Pinned Tweet
    6 Sep 2016

    everyone is about Firth 1957 (you shall know a word...). somehow we all skipped Firth 1935!

    6 replies 34 retweets 63 likes
  2. 18 minutes ago

    note to self: when using own memory allocator, valgrind becomes much less effective at catching bugs.

    2 likes
  3. 2 hours ago

    וועדת משמעת של סטוד׳ שחשודים בהעתקה זה חתיכת דבר מבאס. גם (במיוחד?) כשברור לחלוטין שהקוד שלהם מועתק והם מתעקשים אחרת.

    3 replies 3 likes
  4. In reply to
    Jan 24

    . This is really cool! but I see very few details on how the dataset was constructed. Are you planning a more detailed report?

  5. Jan 24

    Great new dataset for large-scale for text similarity! Excited to try the models developed on 's SNLI corpus on a real task!

    Very excited about this brand new data set by – 400,000 lines of potential question duplicate pairs 📝
    5 replies 17 retweets 60 likes
  6. Jan 22

    For every time we see a neural network architecture with a million widgets and no ablations:

    -- Edsger W. Dijkstra, On the Nature of Computing Science /ht
    1 reply 16 retweets 33 likes
  7. Jan 21

    Coding till 5am, waking up at ~8am because neighbours are renovating. Not very sustainable, let's see how this evolves.

    21 likes
  8. Jan 20

    For those wondering, in latex, - for hyphenation, -- for a range (e.g., 9--12), --- for parenthetical.

    3 retweets 9 likes
  9. Jan 20

    Super happy to announce new major edit of ; new chapters on bias, str. pred. & imitation; other edits, fixes & figs!

    Table of contents. Front matter; Decision Trees; Limits of Learning; Geometry & NN; Perceptron; Practical Issues; Bias & Fairness; Beyond Binary; Linear Models; Probabilistic Models; Neural Networks; Kernel Methods; Learning Theory; Ensembles; Efficient Learning; Unsupervised Learning; EM; Structured Prediction; Imitation learning
    5 replies 126 retweets 346 likes
  10. Jan 21

    ACL revs, if you happen to review this please require ablation studies, or a discussion on which of the very many components does the trick.

    this paper reports strong parsing numbers, but seriously lacks in the interesting part: distilling what's important.
    2 replies 4 retweets 18 likes
  11. Jan 21

    this paper reports strong parsing numbers, but seriously lacks in the interesting part: distilling what's important.

    1 retweet 5 likes
  12. (((λ()(λ() 'yoav)))) followed , and
    • Orgzly
      @Orgzly

      Outliner for notes and tasks in plain-text. Org files on Android. Sync where you choose to.

    • Soumith Chintala
      Verified account
      @soumithchintala

      Facebook AI Research

  13. Jan 19

    Which toolkit are they referring to here?

    4 replies 2 retweets 5 likes
  14. Jan 19

    עקרונות מימון מחקר מדעי 101.

    1 reply 1 retweet 6 likes
  15. Jan 18

    using std::atomic_int for your counter is likely faster than a mutex. I've referenced this post a few times

    1 reply 1 retweet 4 likes
  16. Jan 18

    Are there solutions to variable sharing across threads/cores that ensures visibility and does not require flushes to main mem?

    3 replies 1 like
  17. Jan 18

    I need to wait to k async (threads) calls to finish before proceeding. What is *the cheapest* way to achieve this in c++11?

    2 replies 1 retweet 2 likes
  18. Jan 18

    מי מבין במנגנוני הת׳רדים בסיפפ11? בפרט מה עלויות טיפוסיות של נעילות / שיתופי זכרון בלינוקס, איך מבטיחים משתנה משותף בעלות הנמוכה ביותר וכו.

    1 reply
  19. Jan 17

    Dynamic computation graphs like DyNet & Chainer very useful for —speed looks good—can either make it as mainstream framework?

    Tech report out on Dynamic Neural Net Toolkit DyNet: Design philosophy, internals, and benchmarks with other tools!
    1 reply 28 retweets 66 likes
  20. Jan 17

    Either my new laptop is extremely fast or the people has done a great job, it's really really fast now.

    1 reply 5 retweets 13 likes
  21. Jan 17

    Cool, DyNet ref is out! (incl. comparison c++/py/chainer/tf/theano)

    1 reply 6 retweets 9 likes

@yoavgo hasn't Tweeted yet.

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

    You may also like

    ·