Thomas Miconi

@ThomasMiconi

Neural networks, computational neuroscience, evolutionary computation, artificial life.

SF Bay Area
Vrijeme pridruživanja: rujan 2015.

Tweetovi

Blokirali ste korisnika/cu @ThomasMiconi

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

  1. Prikvačeni tweet
    2. ruj 2015.

    If I have seen further it is by looking where giants didn't.

    Poništi
  2. proslijedio/la je Tweet
    30. sij

    “If you want to advance artificial intelligence, you don’t just do it in a lab,” said Peter Chen [..] “There is a huge gap in bringing it to the real world.” Was wonderful showing the robot in live-production and digging in with and !!

    Poništi
  3. proslijedio/la je Tweet
    29. sij

    The 10 Commandments of Helping Students Distinguish Science from Pseudoscience in Psychology by Scott O. Lilienfeld

    Poništi
  4. proslijedio/la je Tweet
    28. sij

    A clone in the developing cortex. A single neural stem cell labeled at E10 that gave rise to radial glia and newborn neurons in the different cortical layers at E18.5 .

    Poništi
  5. 7. sij

    Guys, I found Reviewer 3’s car!

    Poništi
  6. proslijedio/la je Tweet
    6. sij

    This debunked finding keeps coming back. Humans are at least as good at this task as the chimpanzees. It's a practice effect. See replies in the thread. Good television makes for bad theorizing.

    Prikaži ovu nit
    Poništi
  7. 20. pro 2019.

    Solid performance by today

    Poništi
  8. 19. pro 2019.

    This ONE WEIRD TRICK will make your meta-learning MORE STABLE and POWERFUL! (Except, for real.)

    Poništi
  9. proslijedio/la je Tweet
    18. pro 2019.

    Introducing Generative Teaching Networks, which generate entirely synthetic data that is up to 9x faster to train on than real data!, enabling state-of-the-art Neural Architecture Search Led by w ,, & 1/

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    15. pro 2019.

    You've got to be kidding me. After all these years...

    Prikaži ovu nit
    Poništi
  11. 13. pro 2019.

    If you missed it or didn’t catch everything, you’ll get a second chance at 2:30pm at the Biological and Artificial Reinforcement Learning workshop!

    Prikaži ovu nit
    Poništi
  12. 13. pro 2019.

    . at the Meta-learning workshop, trying to fit an insane amount of science in a single talk

    Prikaži ovu nit
    Poništi
  13. 8. pro 2019.

    “I’ll go register the day before the conference, before 9am”, he thought. “Surely the lines will be totally reasonable”, he thought. He was naive like that.

    Poništi
  14. proslijedio/la je Tweet
    5. pro 2019.

    Try and share your samples Steering to "technology", step size 0.04

    Prikaži ovu nit
    Poništi
  15. 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
  16. 30. stu 2019.
    Poništi
  17. proslijedio/la je Tweet

    Happy 86th birthday to this King. If you used his lecture videos to get an A in any of your math classes you are legally obligated to wish Dr. Gilbert Strang a happy birthday in the comments of this post.

    Prikaži ovu nit
    Poništi
  18. 27. stu 2019.

    The section on "infra-marginality" is very important - and very well done!

    Poništi
  19. proslijedio/la je Tweet

    Four out of eight chapters of our book on fairness and machine learning are now available—halfway there! The newly released chapter is on testing systems for discrimination.. A few thoughts in this thread on why you might find this interesting and useful.

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

    "Self-training with Noisy Student improves ImageNet classification" achieves 87.4% top-1 accuracy. 1 Train a model on ImageNet 2 Generate pseudo labels on unlabeled extra dataset 3 Train a student model using all the data and make it a new teacher ->2

    Poništi
  21. proslijedio/la je Tweet
    7. stu 2019.

    If you are in or around SF, check out this deep learning reading group I've been running since 2018. Only 3 sessions remaining this decade(!) and a line of awesome speakers next year. (Could be you!) Always open for topic/paper/speaker recommendations.

    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:

    ·