Radim Řehůřek

@RadimRehurek

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

Vrijeme pridruživanja: listopad 2013.

Tweetovi

Blokirali ste korisnika/cu @RadimRehurek

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @RadimRehurek

  1. Prikvačeni tweet
    2. srp

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

  2. prije 24 sata

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

  3. proslijedio/la je Tweet
    20. srp
  4. proslijedio/la je Tweet
    19. srp

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

  5. proslijedio/la je Tweet
    20. srp

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

  6. 19. srp

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

  7. proslijedio/la je Tweet
    17. srp

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

  8. proslijedio/la je Tweet
    17. srp
    Odgovor korisnicima i sljedećem broju korisnika:

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

  9. 15. srp

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

  10. proslijedio/la je Tweet
    14. srp
  11. proslijedio/la je Tweet
    14. srp

    This is cool. An adversarial attack library

  12. 14. srp

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

  13. proslijedio/la je Tweet
    12. srp

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

  14. proslijedio/la je Tweet
    12. srp
  15. proslijedio/la je Tweet
    11. srp

    "TextExt - DBpedia Open Extraction Challenge"

  16. proslijedio/la je Tweet
    9. srp

    NoScope: 1000x Faster Deep Learning Queries over Video

  17. 8. srp

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

  18. proslijedio/la je Tweet
    7. srp

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

  19. proslijedio/la je Tweet
    7. srp

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

  20. proslijedio/la je Tweet
    6. srp

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

  21. 6. srp
    Odgovor korisniku/ci

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

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·