Tweetovi

Blokirali ste korisnika/cu @ai_dev_david

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

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

    Trade talks, a prediction: UK - We don't like our deal EU - Why not? UK - We only get 95% of what we want EU - It only gives us 95% too UK - We want a new deal that gives us 100% of what we want EU - But that means we only get 90% of what we want 1/13

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    20. pro 2019.

    Yes! I got my first big conference paper accepted at ICLR, with spotlight! We improve the previous DeepMind paper "NALU" by 3x-20x. – This took 7-8 months, working without any funding as an independent researcher. Paper: Code:

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    9. stu 2019.

    Excited as hell to host my 1st charity livestream with to raise $ for mental health — for 24 hours straight. Amazing peeps will drop by at points inc RTs appreciated!

    Poništi
  4. 12. stu 2019.

    This is for AI masters. Dunno about other programs but I hope it spreads if it turns out well as helpful

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    11. stu 2019.

    all right folks, i'm about to post a thread that's going to endanger the last reliable source of income i have. spoiler: it's yet another example of a gig economy startup brazenly mistreating its workers. let's go!

    Prikaži ovu nit
    Poništi
  6. 7. stu 2019.

    Explainable logic puzzle solver at with interactive demo. Fun demo of an algorithm that can explain itself. :)

    Poništi
  7. 7. stu 2019.

    A wheelchair that automatically avoids crowds at . Interesting how they used standard PC mices to measure wheel movement

    Poništi
  8. 7. stu 2019.

    Just arrived at . Looking forward to some interesting talks!

    Poništi
  9. 6. stu 2019.
    Poništi
  10. proslijedio/la je Tweet

    Our boxology of neuro-symbolic systems is getting quite some traction as a higher level language to talk about about these hybrids (imperfect, but still); I'll be presenting at this week. A nice example of usage is .

    Poništi
  11. proslijedio/la je Tweet
    10. lis 2019.

    sotabench 🏅🛠—This is a great new service by ! It enables benchmarking open-source ML models and comparing the results to what was reported in the paper—directly from GitHub repos. Should be a step towards more replicability in ML!

    Poništi
  12. proslijedio/la je Tweet
    13. ruj 2019.

    “Sapiens” is a timeless masterpiece. Worth reading this book more than once. Some memorable quotes: “There are no gods, no nations, no money and no human rights, except in our collective imagination.” “Our language evolved as a way of gossiping.”

    Poništi
  13. proslijedio/la je Tweet

    Thanks for the thumbs up! We'll call her AI.nstein :-)

    Poništi
  14. proslijedio/la je Tweet
    20. ruj 2019.
    Odgovor korisniku/ci

    There was an interesting paper a year or two ago that compared different approaches to handling class imbalance. They found oversampling the rare class until it's equally frequent was the best approach in every dataset they tested, IIRC.

    Poništi
  15. proslijedio/la je Tweet
    4. ruj 2019.

    Face-to-Parameter Translation for Game Character Auto-Creation Their method allows the automatic creation of game characters based on input face photos. An “imitator” is used to model the behavior of the game engine, to make entire thing differentiable.

    Poništi
  16. 15. kol 2019.
    Poništi
  17. proslijedio/la je Tweet
    2. kol 2019.

    > "AI works like the brain!" Ahh, yes, I fondly remember my intro to linguistics class, wherein I read all of English wikipedia thousands of times until convergence, and then could finally construct better-than-random parse trees.

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet

    I’ve just become aware of an exciting explainer on : Primer, who makes videos about computational biology (ht ). For an example of his work, have a look at this: A Game of Doves and Hawks

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    25. srp 2019.

    "Population Based Training (PBT) is a method first developed at DeepMind that helps discover effective and efficient training regimes for neural nets."? I didn't know DeepMind invented evolutionary algorithms 🤔

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    22. srp 2019.

    “While many RL models have achieved high performance, most demand high computational costs and require significant training time. Using reservoir computing, anyone can quickly train models with much lower computational costs, and importantly, can build highly accurate models.” 😊

    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:

    ·