Tweetovi

Blokirali ste korisnika/cu @lilianweng

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

  1. Prikvačeni tweet
    10. stu 2019.

    😊Self-supervised learning opens up a huge opportunity for better utilizing unlabelled data while learning in a supervised learning manner. My latest post covers many interesting ideas of self-supervised learning tasks on images, videos & control problems:

    Poništi
  2. prije 3 sata

    I just realized that I missed another category of curriculum learning methods, so I added it in. Now the overview figure looks like this:

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

    An Opinionated Guide to ML Research: “To make breakthroughs with idea-driven research, you need to develop an exceptionally deep understanding of your subject, and a perspective that diverges from the rest of the community—some can do it, but it’s hard.”

    Prikaži ovu nit
    Poništi
  4. 30. sij

    Humans learn from curriculum since birth. We can learn complicated math problems because we have accumulated enough prior knowledge. This could be true for training a ML/RL model as well. Let see how curriculum can help an RL agent learn:

    Prikaži ovu nit
    Poništi
  5. 30. sij
    Poništi
  6. 12. sij

    Thank you all! Now I have quite a list of topics to consider, which is likely enough to cover the entire 2020.

    Prikaži ovu nit
    Poništi
  7. 5. sij

    I couldn’t decide the topic of my next post. Would like to hear your ideas. Plz reply! Thanks <3

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    5. pro 2019.

    Over the past 5 months we’ve been experimenting how to steer a mammoth without training it. Here is how.

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    15. lis 2019.

    And yet, it feels like we're just getting started. If you're interested in this line of work, we're hiring for robotics team! I'm quite excited about what we'll be working on in 2020.

    Poništi
  10. 15. lis 2019.

    It has been a long journey for us. There were moments when I felt disappointed or almost hopeless, but the progress we have made, together as a team, is credible. We made it through and made it happen. Check it out!!

    Poništi
  11. proslijedio/la je Tweet
    11. ruj 2019.
    , , i još njih 2
    Prikaži ovu nit
    Poništi
  12. 11. ruj 2019.

    I might be too late into the party, but this Japanese show is so cool: Your turn to kill / あなたの番です —- while watching, you need to take notes, think hard and solve math problem (i.e. hat matching problem). Fun, right?

    Prikaži ovu nit
    Poništi
  13. 6. ruj 2019.

    Would like to thank ! I got the idea of writing this when reading :)

    Prikaži ovu nit
    Poništi
  14. 6. ruj 2019.

    Gradient descent is not the only option when optimizing model parameters. Evolution strategies can help too. Check out my new post if you are interested in how CMA-ES works or the way ES is used in deep RL:

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    11. srp 2019.

    12 years ago I tried making my first poker AI in college and dreamed of beating the world's best pros. After seven years of a PhD, I'm excited to announce that I finally did it! It's been quite an adventure. Looking forward to the next one!

    Poništi
  16. 13. srp 2019.

    Einstein Field Equations - for beginners! —- such a brilliant video, cannot stop watching.

    Poništi
  17. 28. lip 2019.

    This is really cool. You should give it a try if you are training vision models on simulated images 😎

    Poništi
  18. 26. lip 2019.

    Meta RL is a great idea 💡: After trained over a distribution of tasks, an agent is able to solve a new task by developing a new RL algorithm with its internal dynamics. Check my latest blog post if interested:

    Poništi
  19. 9. svi 2019.

    Also this one, approximating CNN as a bag of local features works well on ImageNet:

    Prikaži ovu nit
    Poništi
  20. 9. svi 2019.

    Two most interesting papers I’ve found recently: “the lottery ticket hypothesis” (probably already very famous) and “adversarial examples are not bugs but features”

    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:

    ·