Radim Řehůřek

@RadimRehurek

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

Ekim 2013 tarihinde katıldı

Tweetler

@RadimRehurek adlı kişiyi engelledin

Bu Tweetleri görüntülemek istediğinden emin misin? Tweetleri görüntülemek @RadimRehurek adlı kişinin engelini kaldırmaz.

  1. Sabitlenmiş Tweet
    2 Tem

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

  2. 24 saat önce

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

  3. Retweetledi
    20 Tem
  4. Retweetledi
    19 Tem

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

  5. Retweetledi
    20 Tem

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

  6. 19 Tem

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

  7. Retweetledi
    17 Tem

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

  8. Retweetledi
    17 Tem
    ve kişiye yanıt olarak

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

  9. 15 Tem

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

  10. Retweetledi
    14 Tem
  11. Retweetledi
    14 Tem

    This is cool. An adversarial attack library

  12. 14 Tem

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

  13. Retweetledi
    12 Tem

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

  14. Retweetledi
    12 Tem
  15. Retweetledi
    11 Tem

    "TextExt - DBpedia Open Extraction Challenge"

  16. Retweetledi
    9 Tem

    NoScope: 1000x Faster Deep Learning Queries over Video

  17. 8 Tem

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

  18. Retweetledi
    7 Tem

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

  19. Retweetledi
    7 Tem

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

  20. Retweetledi
    6 Tem

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

  21. 6 Tem
    adlı kullanıcıya yanıt olarak

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

Yükleme biraz zaman alacak gibi görünüyor.

Twitter aşırı kapasiteyle çalışıyor ya da anlık sorunlar yaşıyor olabilir. Yeniden dene ya da daha fazla bilgi almak için Twitter Durumu sayfasını ziyaret et.

    Şunları da beğenebilirsin

    ·