Radim Řehůřek

@RadimRehurek

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

rare-technologies.com
Unit: octubre de 2013
82 fotos i vídeos Fotos i videos

Tuits

Has blocat @RadimRehurek

Estàs segur que vols veure aquests tuits? Això no desblocarà @RadimRehurek.

  1. Tuit fixat
    2 jul.

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

    2 respostes 23 retuits A 70 els agrada
  2. fa 24 hores

    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 retuits A 4 els agrada
  3. ha retuitat
    20 jul.

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

    1 resposta 19 retuits A 38 els agrada
  4. ha retuitat
    19 jul.

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

    4 respostes 112 retuits A 333 els agrada
  5. ha retuitat
    20 jul.

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

    1 resposta 14 retuits A 17 els agrada
  6. 19 jul.

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

    28 retuits A 69 els agrada
  7. ha retuitat
    17 jul.

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

    19 respostes 1.461 retuits A 2.322 els agrada
  8. ha retuitat
    17 jul.
    En resposta a i

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

    2 respostes 5 retuits A 27 els agrada
  9. 15 jul.

    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
    A 4 els agrada
  10. ha retuitat
    14 jul.

    Learn & tricks from our developer at this Sunday! 🐍

    5 retuits A 18 els agrada
  11. ha retuitat
    14 jul.

    This is cool. An adversarial attack library

    Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models
    1 resposta 23 retuits A 55 els agrada
  12. 14 jul.

    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 retuits A 5 els agrada
  13. ha retuitat
    12 jul.

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

    1 resposta 6 retuits A 37 els agrada
  14. ha retuitat
    12 jul.

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

    11 respostes 200 retuits A 458 els agrada
  15. ha retuitat
    11 jul.

    "TextExt - DBpedia Open Extraction Challenge"

    1 resposta 10 retuits A 28 els agrada
  16. ha retuitat
    9 jul.

    NoScope: 1000x Faster Deep Learning Queries over Video

    1 resposta 11 retuits A 34 els agrada
  17. 8 jul.

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

    2 respostes 20 retuits A 75 els agrada
  18. ha retuitat
    7 jul.

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

    4 respostes 224 retuits A 440 els agrada
  19. ha retuitat
    7 jul.

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

    3 respostes 10 retuits A 30 els agrada
  20. ha retuitat
    6 jul.

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

    1 retuit A 20 els agrada
  21. 6 jul.
    En resposta a

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

    1 resposta 16 retuits A 33 els agrada

@RadimRehurek encara no ha tuitat.

Sembla que triga molt a carregar-se.

És possible que el Twitter hagi assolit el límit de capacitat o que experimenti una sobrecàrrega momentània. Torna-ho a provar o vés a l'estat del Twitter si en vols obtenir més informació.

    També et pot interessar

    ·