Radim Řehůřek

@RadimRehurek

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

rare-technologies.com
Регистриран през октомври 2013 г.
82 Снимки и видеоклипове Снимки и видеоклипове

Туитове

Блокираш @RadimRehurek

Наистина ли искаш да видиш тези туитове? Това няма да разблокира @RadimRehurek

  1. Закачен туит
    2.07

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

    2 replies 23 ретуита 70 харесва
  2. преди 24 часа

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

    Two new papers describe agents that learn to imagine and use their imaginations to make plans. Read our blog:
    3 ретуита 4 харесва
  3. ретуитна
    20.07

    Scalnet (keras api in scala) will be more usable next release: great job !

    1 reply 19 ретуита 38 харесва
  4. ретуитна
    19.07

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

    4 replies 112 ретуита 333 харесва
  5. ретуитна
    20.07

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

    1 reply 14 ретуита 17 харесва
  6. 19.07

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

    28 ретуита 69 харесва
  7. ретуитна
    17.07

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

    19 replies 1 461 ретуита 2 322 харесва
  8. ретуитна
    17.07
    В отговор до и още

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

    2 replies 5 ретуита 27 харесва
  9. 15.07

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

    Rank how well your AI demo went: - Great - Good - Ok - Bad - Very Bad - Miyazaki
    4 харесва
  10. ретуитна
    14.07

    Learn & tricks from our developer at this Sunday! 🐍

    5 ретуита 18 харесва
  11. ретуитна
    14.07

    This is cool. An adversarial attack library

    Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models
    1 reply 23 ретуита 55 харесва
  12. 14.07

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

    This stuff is crazy! with ML automated image crop, HDR, and masking for amazing pix from panaramas.
    4 ретуита 5 харесва
  13. ретуитна
    12.07

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

    1 reply 6 ретуита 37 харесва
  14. ретуитна
    12.07

    Python Implementation of the paper () "Depixelizing Pixel Art":

    11 replies 200 ретуита 458 харесва
  15. ретуитна
    11.07

    "TextExt - DBpedia Open Extraction Challenge"

    1 reply 10 ретуита 28 харесва
  16. ретуитна
    9.07

    NoScope: 1000x Faster Deep Learning Queries over Video

    1 reply 11 ретуита 34 харесва
  17. 8.07

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

    2 replies 20 ретуита 75 харесва
  18. ретуитна
    7.07

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

    4 replies 224 ретуита 440 харесва
  19. ретуитна
    7.07

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

    3 replies 10 ретуита 30 харесва
  20. ретуитна
    6.07

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

    1 ретуит 20 харесва
  21. 6.07
    В отговор до

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

    1 reply 16 ретуита 33 харесва

Потребителят @RadimRehurek още не е туитвал.

Изглежда зареждането отнема известно време.

Twitter може да е претоварен или да изпитва моментно затруднение. Опитай отново или виж Twitter Status за повече информация.

    Може също да харесаш

    ·