Tweetovi

Blokirali ste korisnika/cu @nfiedel

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

  1. 28. sij

    Excited to share some of our research into open-domain dialog and natural language response generation (NLG)! Paper: Huge thanks to a fantastic group of collaborators! and more.

    Poništi
  2. proslijedio/la je Tweet
    18. pro 2019.

    Check out a novel approach to out-of-distribution detection, applied to a new benchmark dataset of genomic sequences, that enables a model to better discriminate between anomalous data and that used in training. Learn all about it below ↓

    Poništi
  3. proslijedio/la je Tweet
    13. pro 2019.

    I'm so excited about the program we've put together for Saturday's ML for Creativity and Design Workshop 3.0. Aside from the amazing accepted talks and posters, we have a diverse set of invited speakers I want to highlight in this thread.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    9. pro 2019.

    As promised, we have made the Text-To-Text Transfer Transformer (T5) models much easier to fine-tune for new tasks, and we just released a Colab notebook where you can try it yourself on a free TPU! 👇 (1/3)

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    31. lis 2019.

    We explore a simple approach to task-oriented dialog. A single neural network consumes conversation history and external knowledge as input and generates the next turn text response along with the action (when necessary) as output. Paper: 1/4

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    23. lis 2019.

    New paper! We perform a systematic study of transfer learning for NLP using a unified text-to-text model, then push the limits to achieve SoTA on GLUE, SuperGLUE, CNN/DM, and SQuAD. Paper: Code/models/data/etc: Summary ⬇️ (1/14)

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    16. ruj 2019.

    We ( + + + + ) have now released a Colab notebook where you can play around with some Transformer models for generating piano performances: And the models are trained on transcribed YouTube recordings!

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

    We are excited to release Taskmaster-1, a new task-oriented dialog dataset. We explore two methods for data collection, two-person and self-dialogs. Surprisingly self-dialogs are an effective way to collect dialog. Paper accepted to @emnlp2019 :

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    17. srp 2019.

    There were *21.6M* harmonizations submitted by people to the Bach Doodle!🙀 We are open sourcing this dataset along with a set of fun interactive visualizations to explore the data, discover some familiar top hits and even regional childhood songs! 🎵 📝

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    8. svi 2019.
    Poništi
  11. proslijedio/la je Tweet
    15. sij 2019.

    I promised this a while ago and I finally delivered; I wrote a gosh-darn magnum opus on what I don't like about BLEU & some alternatives you can use instead.

    Poništi
  12. proslijedio/la je Tweet
    13. pro 2018.

    Check out our new blog post on music transformer that generates minute-long pieces that I find myself listening to again! It also generates compelling harmonizations and realizes chord progressions. Which is your favorite? Ours is the Jazz 🎷 👂

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    28. stu 2018.

    We are the first human beings to see a Mars sunset. Its quite a thought.

    Poništi
  14. proslijedio/la je Tweet
    13. stu 2018.

    TensorFlow.js now in Ableton Live via Magenta.js and MaxMSP + Node. Achievement unlocked, congrats to the folks who made this possible!

    Poništi
  15. proslijedio/la je Tweet
    10. stu 2018.

    Hard to believe that 3 years ago, about 20 of us gathered early one morning in a conference room on the 4th floor of Bldg. 1900 for the open-source launch of TensorFlow, watching live Google Analytics stats of & Hacker News comments. We've come a long way!

    Poništi
  16. proslijedio/la je Tweet
    5. stu 2018.

    BLEU is Not Suitable for the Evaluation of Text Simplification, by Elior Sulem, Omri Abend, and Ari Rappoport. EMNLP 2018 short paper.

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    4. stu 2018.

    TensorFlow Serving handles *millions* of QPS inside Google - and it just got easier for everyone to use! You can start with pre-built Docker images for GPU/CPU or compile an image optimised for your specific architecture - all with a single command. Ready for blastoff! 🛠️🚀

    Poništi
  18. proslijedio/la je Tweet
    29. lis 2018.

    AI is a powerful tool for improving society. I'm excited about our AI for Social Good program, focusing on both research & empowering the ecosystem. If you have ideas, submit to the AI Impact Challenge! We're funding the best ideas w/$25M. Learn more at

    Poništi
  19. 18. kol 2018.

    Great analysis and potential for CA to continue innovating and leading the way to large scale, sustainable energy production. If you ever have a chance, I recommend watching Daniel’s talks.

    Poništi
  20. proslijedio/la je Tweet
    21. lip 2018.

    The people who hid Anne Frank were breaking the law. The people who killed her were following it. “Following orders” “doing your job”, or “obeying the law” isn’t an excuse. Period.

    Prikaži ovu nit
    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:

    ·