Radim Řehůřek

@RadimRehurek

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

Uniuse en outubro 2013

Chíos

You blocked @RadimRehurek

Estás seguro de que queres ver estes chíos? Ver os chíos non desbloqueará a @RadimRehurek

  1. Chío pegado
    2 xul

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

  2. Hai 24 horas

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

  3. rechouchiou
    20 xul
  4. rechouchiou
    19 xul

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

  5. rechouchiou
    20 xul

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

  6. 19 xul

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

  7. rechouchiou
    17 xul

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

  8. rechouchiou
    17 xul
    Replying to and

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

  9. 15 xul

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

  10. rechouchiou
    14 xul
  11. rechouchiou
    14 xul

    This is cool. An adversarial attack library

  12. 14 xul

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

  13. rechouchiou
    12 xul

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

  14. rechouchiou
    12 xul
  15. rechouchiou
    11 xul

    "TextExt - DBpedia Open Extraction Challenge"

  16. rechouchiou
    9 xul

    NoScope: 1000x Faster Deep Learning Queries over Video

  17. 8 xul

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

  18. rechouchiou
    7 xul

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

  19. rechouchiou
    7 xul

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

  20. rechouchiou
    6 xul

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

  21. 6 xul
    Replying to

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

Parece que a carga tarda un chisco

É posible que o Twitter estea por riba da súa capacidade ou teña un impo momentáneo. Téntao de novo ou visita o Estado do Twitter para obter máis información.

    Tamén che pode gustar

    ·