Radim Řehůřek

@RadimRehurek

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

Gått med oktober 2013

Tweets

Du blockerade @RadimRehurek

Är du säker på att du vill visa dessa Tweets? Visning av Tweets kommer inte att häva blockeringen av @RadimRehurek

  1. Fastnålad Tweet
    2 juli

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

  2. för 24 timmar sedan

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

  3. Retweetade
    20 juli
  4. Retweetade
    19 juli

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

  5. Retweetade
    20 juli

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

  6. 19 juli

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

  7. Retweetade
    17 juli

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

  8. Retweetade
    17 juli
    Svar till och

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

  9. 15 juli

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

  10. Retweetade
    14 juli
  11. Retweetade
    14 juli

    This is cool. An adversarial attack library

  12. 14 juli

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

  13. Retweetade
    12 juli

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

  14. Retweetade
    12 juli
  15. Retweetade
    11 juli

    "TextExt - DBpedia Open Extraction Challenge"

  16. Retweetade
    9 juli

    NoScope: 1000x Faster Deep Learning Queries over Video

  17. 8 juli

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

  18. Retweetade
    7 juli

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

  19. Retweetade
    7 juli

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

  20. Retweetade
    6 juli

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

  21. 6 juli
    Svar till

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

Hämtningen verkar ta ett tag

Twitter kan vara överbelastat eller ha tillfälliga problem. Försök igen eller besök Twitter Status om du vill ha mer information.

    Du kanske också gillar

    ·