Radim Řehůřek

@RadimRehurek

Applied , , . I like to build practical software. PhD in CS. Founder . Creator . Life in SEA 💘 (🇰🇷).

Připojil se říjen 2013

Tweety

Zablokovali jste uživatele @RadimRehurek.

Opravdu chcete tyto tweety zobrazit? Zobrazením tweetů nedojde k odblokování uživatele @RadimRehurek.

  1. Připnutý tweet
    2. 7.

    Scoping and research analysis finished, starting R&D on real data.

  2. před 24 hodinami

    DeepMind tackles another AI barrier: internal environment simulation. Next up in the GAI quest: simulation of self?

  3. Retweetnuto uživatelem
    20. 7.
  4. Retweetnuto uživatelem
    19. 7.

    The LSTM Strikes Back: sub 60 perplexities on LM PTB (single model). All you need is a (well tuned) LSTM :)

  5. Retweetnuto uživatelem
    20. 7.

    A call for "engineering corpus", to train domain-specific models on. Do you know such corpus? Please RT.

  6. 19. 7.

    A new way to evaluate topic models like LDA: topic intrusion in docs, instead of word intrusion in topics 🎯

  7. Retweetnuto uživatelem
    17. 7.

    Introducing Facets, an open source visualization tool to help understand and analyze datasets

  8. Retweetnuto uživatelem
    17. 7.
    Odpověď uživatelům a

    Thrilled to give a keynote on my fav topic at Warsaw in October: Building practical systems ❤️

  9. 15. 7.

    The old curmudgeon has a point though! Just his definition of "life" is too humane and constraining for the voracious AI crowd.

  10. Retweetnuto uživatelem
    14. 7.
  11. Retweetnuto uživatelem
    14. 7.

    This is cool. An adversarial attack library

  12. 14. 7.

    Already anticipating the startup pitches here 📸 "Instagram Democratized"? "MeUndies for Art"?

  13. Retweetnuto uživatelem
    12. 7.

    I would love to get some feedback from datascientists / kagglers with an extensive experience of feature binning:

  14. Retweetnuto uživatelem
    12. 7.
  15. Retweetnuto uživatelem
    11. 7.

    "TextExt - DBpedia Open Extraction Challenge"

  16. Retweetnuto uživatelem
    9. 7.

    NoScope: 1000x Faster Deep Learning Queries over Video

  17. 8. 7.

    Wow, neat extension of the "hashing trick"! Clean and simple idea for Bloom embeddings by HT

  18. Retweetnuto uživatelem
    7. 7.

    "When not to use deep learning" -- Great article!

  19. Retweetnuto uživatelem
    7. 7.

    What are some things you can do to optimize for iteration speed?

  20. Retweetnuto uživatelem
    6. 7.

    TFW a new contributor does an amazing job, fixing a long standing issue 🏅 Congrats and big thanks to !

  21. 6. 7.
    Odpověď uživateli

    For the impatient: direct links to the datasets (text similarity, entailment, paraphrasing…)

Načítání se zjevně nějak vleče.

Možná je překročena kapacita Twitteru nebo došlo k momentálnímu zablokování. Zkuste to znovu nebo se podívejte na stavovou stránku Twitteru, kde najdete další informace.

    Také by se vám mohlo líbit

    ·