Drew Jaegle

@drew_jaegle

AI, perception, music, philosophy. Researcher at DeepMind. Opinions my own. He/him

London
Vrijeme pridruživanja: prosinac 2015.

Tweetovi

Blokirali ste korisnika/cu @drew_jaegle

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

  1. Prikvačeni tweet
    1. velj 2019.

    Check out our new preprint! We show that a simple neural code, shared by visual cortex and convolutional neural nets, predicts which images will be remembered and which will be forgotten. Surprisingly, this code emerges in CNNs without memory, trained only to classify objects.

    Poništi
  2. 2. velj

    Favorite artist of the new year so far 🐳

    Poništi
  3. proslijedio/la je Tweet
    10. sij

    Very happy to share our latest work accepted at : we prove that a Self-Attention layer can express any CNN layer. 1/5 📄Paper: 🍿Interactive website : 🖥Code: 📝Blog:

    Prikaži ovu nit
    Poništi
  4. 9. sij

    This is fun: an academic whose medium for scholarly book reviews is Amazon 🤯. He's the single greatest influence on my purchasing choices in evolutionary biology texts and printer cartridges so far this year

    Poništi
  5. 7. sij

    Promising work tackling the cross-domain prediction problem at the heart of observational learning of behavior! I'm very happy to see our work on learning how to act from observations (; w/ , , , ) pushed in this way.

    Poništi
  6. 3. sij

    Very nice conversation between and on the work we did during my postdoc! Listen in to learn why we find some images memorable 🧠 and how this computation can drive intelligent behavior in artificial systems 🦾

    Poništi
  7. proslijedio/la je Tweet
    3. sij

    Submissions for our workshop on "Bridging AI and Cognitive Science" at are now open! Submit your recent work, work in progress, or controversial opinions at the intersection of AI and cognitive science.

    Poništi
  8. 25. pro 2019.

    If you're tempted to retweet some particular slice of the acceptance stats you happen to find meaningful: in so doing you're almost certainly amplifying meaningless noise and needlessly increasing pressure on junior researchers.

    Poništi
  9. 25. pro 2019.

    An intriguing perspective from on the adverse effects of institutional dogma on the state of the measurement problem. Understanding considered harmful?

    Poništi
  10. proslijedio/la je Tweet
    20. pro 2019.

    We're pleased to let you know that your submission, On Bonus Based Exploration Methods In The Arcade Learning Environment, has been accepted at ! This huge endeavor was led by . W/ , & . More👇🏼

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    14. pro 2019.

    Come chat with us about equivariant Hamiltonian flows at the Machine Learning and the Physical Sciences workshop! Also come for the talk later today :)

    Poništi
  12. proslijedio/la je Tweet
    6. pro 2019.

    Looking for something to read in your flight to ? Read about Normalizing Flows from our extensive review paper (also with new insights on how to think about and derive new flows) with

    Prikaži ovu nit
    Poništi
  13. 3. pro 2019.
    Poništi
  14. proslijedio/la je Tweet
    28. stu 2019.

    Excited to share our work on Contrastive Learning of Structured World Models! C-SWMs learn object-factorized models & discover objects without supervision, using a simple loss inspired by work on graph embeddings Paper: Code: 1/5

    Prikaži ovu nit
    Poništi
  15. 29. stu 2019.

    Statistical models and other science fiction

    Poništi
  16. proslijedio/la je Tweet
    21. stu 2019.
    Poništi
  17. proslijedio/la je Tweet
    20. stu 2019.

    We beta-released the IKEA Furniture Assembly environment for solving long-term manipulation tasks with high-quality rendering. * 80+ furniture models * Multiple robots * Various observations * Supports OpenAI gym Try it out and let us know what you think!

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    15. stu 2019.

    wishing I could make content this sublime

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    13. stu 2019.

    Fellow ACs: the discussion period ends this Friday. It's YOUR JOB to ensure the review process is fair and bad reviews (even written w/ good intentions) come out in the wash. If you can't hold reviewers to account, there is no point in pretending peer review matters.

    Poništi
  20. 14. stu 2019.
    Poništi
  21. proslijedio/la je Tweet

    Umm. Bill Gates... doesn't say what's widely claimed on Twitter. I'm not a fan. I think Microsoft happened because of its monopoly position that it *still* benefits from. But he's clearly saying he'll vote Warren if the nominee despite thinking wealth tax will be huge for him.

    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:

    ·