Dzmitry Bahdanau

@DBahdanau

PhD student at Université de Montréal

Vrijeme pridruživanja: kolovoz 2017.

Tweetovi

Blokirali ste korisnika/cu @DBahdanau

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

  1. prije 17 sati

    Do you need to remove comments from the source code before uploading it to CMT for ICML? Try this: find . -type f -name "*.py" -print0 | xargs -0 sed -i '/^[[:blank:]]*#/d;s/#.*//' P.S.: cudos to stackoverflow as usual

    Poništi
  2. 18. sij

    I have to post this as well:

    Prikaži ovu nit
    Poništi
  3. 18. sij

    I found it very important to learn basics of LISP to start understanding symbolic AI literature. It seems like this programming language for many decades structured the way people thought and communicated with each other.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet

    We're coming to Ukraine, with a great set of speakers. Looking forward to see you there and spread the word!

    Poništi
  5. 19. pro 2019.

    FYI: our BabyAI paper has been updated to contain more accurate sample efficiency estimates.

    Poništi
  6. 13. pro 2019.

    We present CLOSURE, a systematic generalization test for visual reasoning models trained on the CLEVR dataset. Come to the poster session at Visually Grounded Interaction and Language Workshop to learn more!

    Poništi
  7. 8. pro 2019.

    Very important question: closest decent climbing gym to the conference center in Vancouver? Another important question: who else wants go? ;)

    Poništi
  8. 2. stu 2019.

    one great thing about writing a PhD thesis is learning just how vast the history of AI is and just how little related work most papers cite...

    Poništi
  9. 2. ruj 2019.

    Just received an email from AAAI organizers, saying that the reviewer load will be 5-10 (10!!!) papers, that all requests to lower the load were ignored, and that "Unless you are able to take on a full load, you should withdraw from the PC". Strikes me as not constructive.

    Poništi
  10. 21. svi 2019.

    My colleagues received a rejection notification from ACL after the arXiV freeze has started for EMNLP. Now they again can't publicly share their work with others. The effective publication date is thus shifted by 6 months. Working as intended??

    Poništi
  11. 15. svi 2019.

    more awesome research on (the lack of) generalization

    Poništi
  12. 11. svi 2019.

    brought to you by , myself, , , , Yoshua Bengio

    Prikaži ovu nit
    Poništi
  13. 11. svi 2019.

    If you want to do research on instruction following and/or language grounding, consider using our BabyAI platform: 10^19 synthetic instructions, 19 levels of varying difficulty. Work done by with the help of .

    Prikaži ovu nit
    Poništi
  14. 11. svi 2019.

    For me, the turning point was reading this article on `git` internals: . It's was like reading a linear algebra textbook and all of a sudden understanding what this PyTorch thing actually does ;)

    Prikaži ovu nit
    Poništi
  15. 11. svi 2019.

    Researchers, you don't know it yet, but y'all want to take 2 days off and *really* learn to use git. Not just remember 2 basic commands, but understand how this beautiful piece of software works and how much it can help with reproducibility and collaboration.

    Prikaži ovu nit
    Poništi
  16. 15. tra 2019.

    and Thien's Twitter incarnation is

    Prikaži ovu nit
    Poništi
  17. 15. tra 2019.

    thanks to my amazing coauthors: Thien Huu Nguyen

    Prikaži ovu nit
    Poništi
  18. 15. tra 2019.

    Are you curious about systematic generalization? Do you like small, carefully controlled studies with intriguing conclusions? Check out our latest paper: . Code & data at . Work done by with the help of

    Prikaži ovu nit
    Poništi
  19. 21. ožu 2019.

    the perfect argument supporting my belief that large scale language modelling won't deliver robust language understanding

    Poništi
  20. 2. ožu 2019.

    Dear Twitter, can you recommend me a good account of what kind and what amount of language human children are exposed in their first, say, 7 years of life?

    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:

    ·