rosemary ke

@rosemary_ke

PhD student at Mila, interested in credit assignment and causal learning.

Montreal, Canada
Vrijeme pridruživanja: srpanj 2011.

Tweetovi

Blokirali ste korisnika/cu @rosemary_ke

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

  1. 15. sij

    The submission deadline for our causal learning for decision making workshop is Feb 10th. The submission portal is . Our workshop website is

    Poništi
  2. 9. sij

    We are organizing an ICLR workshop on causal learning for decision making. Understanding causality and its role in the decision making progress posses interesting challenges.

    Poništi
  3. 30. pro 2019.

    A talk about our paper can be found at Yoshua's NeurIPS 2019 keynote lecture. The video and slides are available at

    Poništi
  4. 30. pro 2019.

    We have released our code for "Neural causal learning from unknown interventions" here . The paper is here . joint work with Olexa Bilaniuk, , , , Yoshua Bengio

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

    See, also the followup to this led by : )

    Prikaži ovu nit
    Poništi
  6. 14. pro 2019.
    Poništi
  7. proslijedio/la je Tweet
    13. pro 2019.

    I strongly agree with this. Data distribution should be growing (adding more tasks more time) , composite (combination of two or more sub-tasks) as well as diverse (various different tasks).

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    13. pro 2019.

    I will be presenting our poster on extracting signals in the frequency domain with Deep Complex Extractors in the Deep Inverse Problems workshop at from 4:15pm to 6:00 pm. Don't hesitate to come by and ask questions.

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

    Yoshua Bengio talking about "why backprop is not biologically plausible"

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

    Coming to and want to discuss generative models, overshoot, memory and RL? Come see our poster on Thursday! "Shaping Belief States with Generative EnvironmentModels for RL" East Exhibition Hall B + C #234

    Poništi
  11. proslijedio/la je Tweet

    There’s a simple way to fight familiarity bias. When you read a good paper with an author you don’t know, especially if they’re junior, take a minute to look them up, get to know their work, cite them, and keep them in mind for events you organize. In short, remember the name!

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

    Due to the mismatch in timezone deadlines on the website, authors will be able to submit responses and paper updates till 2pm PDT (15 Nov).

    Poništi
  13. proslijedio/la je Tweet

    Deadline extended to Nov 8th PDT for claiming a paper to reproduce! Still time to participate in the challenge!

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet

    Here's a tip if you want to get more reads on your paper Do a short Youtube video about your paper. YT is a search engine with the google algorithm. You can make the algorithm work for you and get a lot of traffic I can record a more detailed explanation

    Poništi
  15. 25. lis 2019.

    Neurips reprpducibity challenge registration is due in a week!

    Poništi
  16. 14. lis 2019.

    Attending the IAS workshop, will be presenting our work on neural causal learning from unknown interventions. 😃

    Poništi
  17. proslijedio/la je Tweet
    25. ruj 2019.

    This is what I've been doing for quite some time. Recurrent Independent Mechanisms (RIMs) , joint work with Alex Lamb, , , , and Yoshua Bengio. Here's a short summary:

    Prikaži ovu nit
    Poništi
  18. 8. lis 2019.

    Our recent papers on learning neural causal models from unknown interventions featured on Wired, (, )

    Poništi
  19. 5. lis 2019.

    Here, we look at the setting where interventions are unknown, and our goal is to discover causal graphs given unknown-intervention samples.

    Prikaži ovu nit
    Poništi
  20. 5. lis 2019.

    Our new work on learning Neural Causal Models from unknown interventions! In the real world, interventions are also not always performed by an experimenter. They can be performed by other agents, or by environmental changes in unknown ways and hence are unknown to the model.

    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:

    ·