Radim Řehůřek

@RadimRehurek

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

Registrerte seg oktober 2013

Tweets

Du har blokkert @RadimRehurek

Er du sikker på at du vil vise disse tweetene? Dette vil ikke oppheve blokkeringen av @@RadimRehurek.

  1. Festet tweet
    2. jul.

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

  2. for 24 timer siden

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

  3. Retweetet
    20. jul.
  4. Retweetet
    19. jul.

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

  5. Retweetet
    20. jul.

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

  6. 19. jul.

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

  7. Retweetet
    17. jul.

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

  8. Retweetet
    17. jul.
    Svar til og

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

  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.

  10. Retweetet
    14. jul.
  11. Retweetet
    14. jul.

    This is cool. An adversarial attack library

  12. 14. jul.

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

  13. Retweetet
    12. jul.

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

  14. Retweetet
    12. jul.
  15. Retweetet
    11. jul.

    "TextExt - DBpedia Open Extraction Challenge"

  16. Retweetet
    9. jul.

    NoScope: 1000x Faster Deep Learning Queries over Video

  17. 8. jul.

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

  18. Retweetet
    7. jul.

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

  19. Retweetet
    7. jul.

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

  20. Retweetet
    6. jul.

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

  21. 6. jul.
    Svar til

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

Lastingen ser ut til å ta sin tid.

Twitter kan være overbelastet, eller det kan ha oppstått et midlertidig problem. Prøv igjen, eller se Twitters status for mer informasjon.

    Du vil kanskje også like

    ·