Rezultati pretraživanja
  1. Osobe Vidi sve

  2. 11. pro 2019.

    Our dataset, ObjectNet, a new kind of object recognition dataset that includes controls for biases, is being released at this week. Removing biases leads to a sharp drop in performance, opening the way to more robust computer vision.

  3. 1. velj

    Not sure if many fraudsters attend the big ML conferences (is there a fraudster workshop at or ?) but I'd be shocked if there weren't some that use ML.

    Prikaži ovu nit
  4. 31. sij

    Questions continued into lunch where policy researcher asked about democratising vs pricing data and the effectiveness of regulation. A great chance to reconnect with and continue conversations from the AI for Social Good workshop at

    Prikaži ovu nit
  5. 31. sij

    The comments about diversity at conferences resonates with what I saw at . Glad to hear about efforts underway at

  6. Odgovor korisniku/ci

    Existe o perigo de se repetir o que vemos em outras áreas. Os gigantes sempre conseguem tolerar certos níveis de regulação que aos pequenos só resta fechar as portas. Mas ao menos em IA tenho visto os principais players com uma postura bem comunitária / transparente

  7. 30. sij
    Odgovor korisniku/ci

    That gives me hope! If even you started late and still managed to keynote !

  8. 29. sij
  9. 世界のAI学会「NeurIPS」のコンペが激戦に、競り勝って入賞した日本勢とは

  10. 27. sij
  11. 27. sij
  12. 18. sij

    Papers are published online - conferences should be too!!! More attendees ($30 instead of $2000+, no visa issues) More content (anyone could stream a talk) More often ( every quarter) Seems like a no brainer Would you go to an ?

  13. 11. sij

    Really proud of being editor of the special issue of on the theory Machine learning with long version of papers from 2018 , & . They are some real gems in there!

  14. 8. sij

    "What I found at Black In AI was a lot of work questioning basic assumptions of a field which has moved from the margin to the spotlight (literally half of the commercial booths at were hedge funds)" A superb summary & reflection by

    Prikaži ovu nit
  15. 7. sij

    A pretty amazing lineup of papers related to statistical physics & machine learning from 2018 , & in now collected in . See and enjoy :)!

  16. Read my latest blog post detailing recent events around naming of and parallels it shares with name change. Also cluelessness of privileged men like and Aaronson Happy holidays!

    Prikaži ovu nit
  17. 19. pro 2019.

    Takeaways from : 1) In-distribution generalization is out 2) Out-of-distribution generalization is in 3) We want compositionality (whatever it is) 4) "GPT-2" is very hard to say

  18. 14. pro 2019.

    Slides for my 2nd NeurIPS talk. "Materials Matter: How biologically inspired alternatives to conventional neural networks improve meta-learning and continual learning" Covers Differentiable Plasticity & ANMML

  19. 13. pro 2019.

    I know it’s but it still needs to be said: if you’re working with generated templates, you have not made a “natural language understanding system”.

  20. 12. pro 2019.

    Looking forward for workshops tomorrow - my favorite part of . and I will speak about the MEMENTO observation in Atari agents tomorrow at 4:15 in the BARL workshop. Come see us at the poster! , , yoshuawonttweet,

  21. 12. pro 2019.

    Me at the poster session when I see a paper I reviewed and fought for accepting

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.