Tweetovi

Blokirali ste korisnika/cu @tcs2711

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @tcs2711

  1. proslijedio/la je Tweet

    We have a new research award opportunity on the topic of on-device AI! Academic faculty can submit proposals on enabling execution of AI-based capabilities within the constraints of edge devices. Applications are open until February 3.

    Poništi
  2. 14. stu 2019.
    Poništi
  3. proslijedio/la je Tweet
    4. stu 2019.

    ⚙️Release: CCNet is our new tool for extracting high-quality and large-scale monolingual corpora from CommonCraw in more than a hundred languages. Paper: Tool: By G. Wenzek, M-A Lachaux, ,

    Poništi
  4. proslijedio/la je Tweet

    Facebook AI has achieved superhuman performance on English to German translation tasks, according to organizers. Read more:

    Poništi
  5. proslijedio/la je Tweet
    5. kol 2019.
    Poništi
  6. 11. srp 2019.
    Poništi
  7. proslijedio/la je Tweet
    11. lip 2019.

    ICML2019Tutorial資料集(1/2) Attention in Deep Learning Meta-Learning: from Few-Shot Learning to Rapid Reinforcement Learning Never-Ending Learning A Primer on PAC-Bayesian Learning

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    2. lip 2019.
    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    3. svi 2019.

    Interesting developments happened in 2018/2019 for natural language generation decoding algorithms: here's a thread with some papers & code So, the two most common decoders for language generation used to be greedy-decoding (GD) and beam-search (BS). [1/9]

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet

    Accepted to ! :) (didn't expect this, we got both a strong accept and a strong reject)

    Poništi
  11. proslijedio/la je Tweet
    16. tra 2019.

    Useful Linux cheat sheet for data scientists

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    16. tra 2019.

    I wrote a starter pack for Landmark Retrieval 2019 competition. Since the competition data is too huge to iterate quickly, I have used SfM120k dataset from GeM paper. All the validation, fast NN-search code is already there. Library is

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    3. tra 2019.

    This is really neat! You take a screenshot of an equation, it gives you the LaTeX code, you can directly modify in the taskbar, copy, paste, done.

    Poništi
  14. proslijedio/la je Tweet
    19. ožu 2019.

    We are organizing the first Southeast Asia Machine Learning School (, , Adhi). Grateful to our sponsors (, , many others) and awesome speakers ( , , ++). Application is now open, please help share!

    Poništi
  15. proslijedio/la je Tweet

    Excited to announce the first Southeast Asia Machine Learning School to be held in Jakarta, Indonesia from July 8-12, 2019. Application is now open until April 20, 2019. Please apply on our website!

    Poništi
  16. proslijedio/la je Tweet
    23. velj 2019.
    Prikaži ovu nit
    Poništi
  17. 12. stu 2018.
    Poništi
  18. 11. lis 2018.
    Poništi
  19. proslijedio/la je Tweet
    7. lis 2018.

    AKA "friends don't let friends use VGG"

    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:

    ·