Radim Řehůřek

@RadimRehurek

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

Iscritto a ottobre 2013

Tweet

Hai bloccato @RadimRehurek

Sei sicuro di voler vedere questi Tweet? Visualizzare i Tweet non sbloccherà @RadimRehurek

  1. Tweet fissato
    2 lug

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

  2. 24 ore fa

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

  3. ha ritwittato
    20 lug
  4. ha ritwittato
    19 lug

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

  5. ha ritwittato
    20 lug

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

  6. 19 lug

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

  7. ha ritwittato
    17 lug

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

  8. ha ritwittato
    17 lug
    In risposta a , e

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

  9. 15 lug

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

  10. ha ritwittato
    14 lug
  11. ha ritwittato
    14 lug

    This is cool. An adversarial attack library

  12. 14 lug

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

  13. ha ritwittato
    12 lug

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

  14. ha ritwittato
    12 lug
  15. ha ritwittato
    11 lug

    "TextExt - DBpedia Open Extraction Challenge"

  16. ha ritwittato
    9 lug

    NoScope: 1000x Faster Deep Learning Queries over Video

  17. 8 lug

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

  18. ha ritwittato
    7 lug

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

  19. ha ritwittato
    7 lug

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

  20. ha ritwittato
    6 lug

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

  21. 6 lug
    In risposta a

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

Il caricamento sembra essere lento.

Twitter potrebbe essere sovraccarico o avere un problema temporaneo. Riprova o visita Twitter Status per ulteriori informazioni.

    Potrebbero piacerti

    ·