Tweetovi

Blokirali ste korisnika/cu @O87623028

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @O87623028

  1. proslijedio/la je Tweet
    25. sij

    I hope not everyone in those PhD committees think like this. You are valuing quality of writing over achievements (as depicted in a CV.) You are favoring native English speakers over those whose first language is not English. Scary.

    Poništi
  2. proslijedio/la je Tweet
    23. sij

    Google Dataset Search is now officially out of beta. "Dataset Search has indexed almost 25 million of these datasets, giving you a single place to search for datasets & find links to where the data is." Nice work, Natasha Noy and everyone else involved!

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    17. sij

    After a year of dev, I am *extremely* excited to share this step-by-step tutorial Goal: to be the *easiest* intro to preserving, Deep Learning It's in I hope you enjoy it

    Poništi
  4. proslijedio/la je Tweet
    17. pro 2019.

    Want to catch up on some latest Deep RL work? Here is a zip file with all the camera-ready papers from the Deep RL Workshop!

    Poništi
  5. proslijedio/la je Tweet

    It is that time of the year where many aspirants will be applying for grad school and tenure track positions. I just wanted to share some advice that I wish I had known when I was going through these things. [continued below]

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    21. stu 2019.

    We're releasing Safety Gym, environments and tools to evaluate reinforcement learning with safety constraints: Aims to ultimately help agents satisfy real-world safety requirements while training (eg not driving off a cliff, not writing abusive content).

    Poništi
  7. proslijedio/la je Tweet
    21. stu 2019.

    Interesting claim by : "The future is Multi-Agent!"

    Poništi
  8. proslijedio/la je Tweet
    20. stu 2019.

    Exciting new paper from : Planning with **learned** models can scale to complex visual domains like Atari. TL;DR: MCTS + Q-learning with models that only predict rewards/Q-values leads to new SOTA on Atari games and matches AlphaZero on Go.

    Poništi
  9. proslijedio/la je Tweet
    18. stu 2019.

    A long time ago— like 15 years ago— I worked at Sun Microsystems. The company was nearly dead at the time (it died a couple years later) because they didn't make anything that anyone wanted to buy anymore. So they had a lot of strange ideas about how they'd make their comeback.

    Prikaži ovu nit
    Poništi
  10. 18. stu 2019.
    Poništi
  11. proslijedio/la je Tweet
    13. stu 2019.

    It's rare to find an original take in stories about Nay Pyi Taw, but here's a great read about "the ghost town without ghosts" by

    Poništi
  12. proslijedio/la je Tweet
    12. stu 2019.

    We are putting an End to End-to-End! Check out the camera-ready version of our paper selected for an oral presentation : W/ & Peter O’Connor We also published our code:

    Poništi
  13. proslijedio/la je Tweet
    11. stu 2019.

    François Chollet’s core point: We can't measure an AI system's adaptability and flexibility by measuring a specific skill. With unlimited data, models memorize decisions. To advance AGI we need to quantify and measure ***skill-acquisition efficiency***. Let’s dig in👇

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet

    Introverts have a lot to offer.

    Poništi
  15. proslijedio/la je Tweet
    30. lis 2019.
    Poništi
  16. proslijedio/la je Tweet

    Oh my fucking god.

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    25. lis 2019.

    UCL AI Centre doing its bit to train next generation AI leaders.

    Poništi
  18. proslijedio/la je Tweet
    24. lis 2019.

    The paper on meta-world -- a new benchmark for meta-learning with 50 distinct robotic manipulation tasks -- is now out! Code & documentation here: Full paper:

    Poništi
  19. proslijedio/la je Tweet
    26. ruj 2019.
    Poništi
  20. proslijedio/la je Tweet
    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:

    ·