Tweetovi

Blokirali ste korisnika/cu @ykashnitsky

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

  1. 31. sij

    Thanks to for all their cool work, both in industry and academia (+Kaggle) NLP practitioners know them, mostly for Transformers. In a new release Dutch BERT is shared, thanks to & Co. That's a big step for all Dutch NLP community

    Prikaži ovu nit
    Poništi
  2. 23. pro 2019.

    Those reviews by describe what’s happening on the frontier of today’s NLP.

    Poništi
  3. 7. pro 2019.

    Catalyst turns DL researchers into better developers. Transformers by helps you climb the shoulders of NLP giants. I started building a bridge between the two Tnx to for support. When they merged my PR I has already turned into a dad

    Poništi
  4. 18. stu 2019.

    In this talk, I'll describe the learning path you need to step in to find your first Data Science job. Assuming that basic Machine Learning is covered (, Andrew Ng's course or similar). This Saturday, 9am-11am GMT

    Poništi
  5. 13. lis 2019.

    When they compare my activity with Suraj Raval 's "AI education", I'll show this.

    Poništi
  6. 4. ruj 2019.

    Last session of has recently started, high time to join. Just manage to survive - and you'll remember these 11 weeks. Several Kaggle Inclass competitions, assignments, quizzes - both theory and practice. Nice to see our repo trending on GitHub.

    Poništi
  7. 26. kol 2019.

    A podcast on - how the course was born in 2017, how it's different from other courses. We also discuss best ways to get DS job when basic ML is covered. Thanks to Sanyam for this interview. Some more details are found in this post

    Poništi
  8. 19. kol 2019.
    Poništi
  9. 19. kol 2019.

    Seen in ∏ρ؃uñçτØρ Øπτµç∑

    Poništi
  10. 9. kol 2019.

    Nice example of achieving pretty decent sentiment prediction accuracy without Deep Learning.

    Poništi
  11. 4. kol 2019.
    Poništi
  12. 9. srp 2019.

    A review of 10 AI courses at done by It's one-year old, but I found it really helpful. Her blog also deserves attention , eg. this overview of main ICLR2019 trends

    Poništi
  13. proslijedio/la je Tweet
    8. srp 2019.

    Excited to share our newest course: A Code-First Introduction to Natural Language Processing All code & videos are available for free online, please check it out!

    Prikaži ovu nit
    Poništi
  14. 26. svi 2019.

    neither does bayesian optimization yet help

    Poništi
  15. 21. svi 2019.

    Got accepted to the workshop, our paper is based on the competition "Gendered Pronoun Resolution". 1) Our model performs pronoun resolution with 92% F1 as compared to Google AI's 74% 2) our BERT-based model is gender-unbiased

    Poništi
  16. 2. svi 2019.

    The last session of will start on September 2, take your chance! The recently finished session was focused on competitions, it was a great experience for those 1600 participants. For the final session we'll prepare smth new

    Poništi
  17. 1. svi 2019.

    It's easy to agree with Yann LeCun, but here I totally agree. "Self-supervised learning" is a much better term for such tasks where data itself provides labeling, ex. Word2Vec (predicting words given context), language modelling, BERT etc.

    Poništi
  18. 28. tra 2019.

    One more competition where ULMFiT by @ Co. smashed all alternative approaches …. It's clickbait news detection. Waiting for a "serious" competition (not In-class) purely to test SSL and transfer learning NLP approaches

    Poništi
  19. 10. velj 2019.

    Tomorrow we start a new, competition-focused session of . It will be perfect for those who've only stepped on their long Kaggle path. Thanks to Kaggle CEO for sharing

    Poništi
  20. 16. sij 2019.

    New session of , open Machine Learning course by takes off on Feb 11 and will be much more focused on competitions. If you'd like to quickly dive into the world of , this course is for you

    Poništi

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:

    ·