Tweetovi

Blokirali ste korisnika/cu @shelling343

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @shelling343

  1. 18. lis 2019.

    Such a great notebook. That's my new textbook of GP :)

    Poništi
  2. 30. kol 2019.

    Shouldn't blame too much on reviewers. It's an art to let someone accepting your idea. That's a topic through my whole PhD, but didn't master it yet.

    Poništi
  3. 28. srp 2019.
    Poništi
  4. 8. srp 2019.
    Poništi
  5. proslijedio/la je Tweet
    1. srp 2019.

    Deep RL agents are data hungry and often learn task-specific representations. Our model learns object-centric abstractions from raw videos. This enables highly data-efficient RL and structured exploration.

    Poništi
  6. proslijedio/la je Tweet
    9. svi 2019.

    One of the hardest problems in robotics is that models trained in simulator normally do not work on real robots. Domain randomization is a simple but powerful idea to close this sim2real gap:

    Poništi
  7. proslijedio/la je Tweet
    11. lip 2019.

    Weight Agnostic Neural Networks 🦎 Inspired by precocial species in biology, we set out to search for neural net architectures that can already (sort of) perform various tasks even when they use random weight values. Article: PDF:

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

    RUNN = 🏃‍♂️Run (side-scrolling game) + 🤖RNN 🎉 I build the game to make machine learning fun! The whole game is generated as music by RNN model. 👉 demo: 👨‍💻 source: ✍️ blog:

    Poništi
  9. proslijedio/la je Tweet
    4. lip 2019.

    Hey, I wrote that! Yes, do download it! :-)

    Poništi
  10. proslijedio/la je Tweet
    4. lip 2019.

    Evolution gave our visual system useful priors for prediction. These illusions show that the way humans predict the future might be really different than say, a video prediction algorithm trained to predict the next frame. Our visual system cuts corners and cheats for efficiency.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    8. ožu 2019.

    Ignite Her Curiosity: 70 Books to Inspire Science-Loving Mighty Girls | A Mighty Girl

    Poništi
  12. 4. pro 2018.
    Poništi
  13. proslijedio/la je Tweet
    27. lip 2018.

    Efficient inference and learning for undirected probabilistic graphical models now on with our intern Xu Hu from

    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:

    ·