hardmaru

@hardmaru

research scientist at google brain 🧠 香港人 🏴

東京
Vrijeme pridruživanja: studeni 2014.

Medijski sadržaj

  1. prije 7 sati
    Prikaži ovu nit
  2. prije 7 sati

    Mask designed to protect the wearer from the virus in the Sea of Corruption

    Prikaži ovu nit
  3. 2. velj
    Odgovor korisniku/ci
  4. 1. velj
  5. 1. velj

    Rotation, Translation, and Cropping for Zero-Shot Generalization Makes a lot of sense. Try playing Doom not from an agent-centric perspective! I think agent-centric view is a better prior for encoding useful information using fewer bits for the policy.

  6. 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
  7. 29. sij

    Machine Unlearning “Once users have shared their data online, it is difficult to revoke access and ask for the data to be deleted. ML exacerbates this problem because any model trained with said data may have memorized it, putting users' privacy at risk.”

    Prikaži ovu nit
  8. 28. sij

    Procedural Content Generation via Reinforcement Learning “A new approach to procedural content generation in games, where level design is framed as a game (as a sequential task problem), and the content generator itself is learned.”

  9. 28. sij

    Using OpenAI Gym and PyBullet to train an open-source 3D printed robot

  10. 26. sij

    USD salary vs Year “Tech favors the young. For people with more than 15 years of experience, there’s practically no correlation between years of experience and income (corr < 0). After 15 years, you either retire, switch to management, or change career.”

    Prikaži ovu nit
  11. 23. sij

    Interactive demo to see how IEEE floats are represented

  12. 23. sij

    Plotting out every road in Hong Kong

    Prikaži ovu nit
  13. 23. sij
    Prikaži ovu nit
  14. 22. sij

    “Companies such as ours cannot just build promising new technology and let market forces decide how it will be used. [Examples of] areas where we will not deploy AI, such as to support mass surveillance or violate human rights.” Article by

  15. 22. sij

    BayesNet: A library for drawing Bayesian networks, graphical models and directed factor graphs in LaTeX.

  16. 21. sij

    My ideal neural network library should be like this tiny house.

  17. 20. sij

    Community-Organised vs Government Organised Lunar New Year Market in Hong Kong

    Prikaži ovu nit
  18. 20. sij

    Flax: A neural network library for JAX designed for flexibility (pre-release)

  19. 19. sij
  20. 19. sij

    If you like this one consider buying some prints from the artist:

    Prikaži ovu nit

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:

    ·