Tweetovi

Blokirali ste korisnika/cu @SudhakaranShyam

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

  1. proslijedio/la je Tweet
    20. pro 2019.

    Sup maths nerds happy holidays

    Poništi
  2. proslijedio/la je Tweet
    27. stu 2019.

    “I don’t want to go for a walk dad, I look stupid”

    Poništi
  3. 26. stu 2019.
    Poništi
  4. proslijedio/la je Tweet
    18. ruj 2019.

    Just posted “Ludwig: a type-based declarative deep learning toolbox”, a paper describing the design of and the motivations behind its architecture:

    Poništi
  5. proslijedio/la je Tweet
    17. ruj 2019.

    We've observed AIs discovering complex tool use while competing in a simple game of hide-and-seek. They develop a series of six distinct strategies and counterstrategies, ultimately using tools in the environment to break our simulated physics:

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    9. ruj 2019.

    A paper I co-authored with Kian Sheik last semester is featured in an article on TechXplore. We collected a TON of music data and learned a few things about the magic sauce behind hit songs. Check it out! Thanks for writing a great article !

    Poništi
  7. proslijedio/la je Tweet

    🎉We are pleased to announce the 3rd edition of the reproducibility challenge at ! 🎉 Researchers and students at all levels are encouraged to participate. Registration Deadline: Nov. 1 2019 Report Submission Deadline: Dec. 1 2019

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    29. kol 2019.

    Did you know when you take the geometric mean of several distributions, you're minimizing a KL divergence? In this post, I show how the geometric mean is related to the KL divergence, and how we can use this relation for training from noisy labels. Post:

    Poništi
  9. proslijedio/la je Tweet
    22. srp 2019.

    SentiMATE: Learning to play Chess through Natural Language Processing by Isaac Kamlish et al.

    Poništi
  10. proslijedio/la je Tweet

    Lyft open-sourced their autonomous driving dataset from its Level 5 self-driving fleet. - 55k human-labeled 3D frames - 7 cameras, 3 lidars - HD spatial semantic map: lanes, crosswalks, etc - Drivable surface map

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

    Thought I'd share something on !! I'm André and I'm a Game Designer with a Youtube channel called Mix and Jam - where I recreate mechanics from games using and explain the steps I followed to achieve them! Check it out here: !

    Poništi
  12. proslijedio/la je Tweet
    20. svi 2019.

    Really interesting work being done by a group at Oxford to build a multi-agent platform on top of ML-Agents and Unity

    Poništi
  13. proslijedio/la je Tweet
    5. tra 2019.

    I'm excited to share our new preprint out on arXiv today. We combine a deep neural network that predicts the future with a small, evolving network that adapts the agent's goals. Those adaptive goals are able to transfer the predictive model to new tasks.

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    1. tra 2019.

    "GAN You Do the GAN GAN?": Training GANs over snapshots of GANs. Paper PDF (<3 pages) + source at …. arXiv link live soon. Happy April 1! Back on neural mmo tomorrow.

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    29. ožu 2019.
    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:

    ·