Tweetovi

Blokirali ste korisnika/cu @SelfOrgAnna

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

  1. proslijedio/la je Tweet
    3. velj
    Poništi
  2. proslijedio/la je Tweet
    11. sij

    You wanna do something for the climate this year? Fine, how about refraining from flying distances under a 1000km? Here is your campaign by to sign and please RT

    Poništi
  3. proslijedio/la je Tweet
    17. sij

    So far was not good at combinatorial/algorithmic problems. For instance, anything involving to sort something or solving a planning problem. However, classical algorithms are great at it. We enable many such algorithms to be a building-block of deep architectures.

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

    We were excited to see that our paper Differentiation of Blackbox Combinatorial Solvers was one of the top-rated papers at OpenReview 🥳. We are looking forward to where we will present it as a spotlight!

    Poništi
  5. proslijedio/la je Tweet

    "Maintaining a life-sustaining & life-fulfilling planet for humans & other species are ...one & the same challenge—a challenge that cannot be met by business as usual." Only immediate transformative change will sustain nature as we know it

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

    The first real application of is out there! It can out-of-the-box differentiate the ranking function (just by calls to torch.argsort) and help directly optimize rank-based metrics. Simple, blazing-fast, and about on-par with SOTA!

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

    Interested in , intrinsic motivation and planning? Check out our new paper: Control what you can... We are presenting at today morning, Poster 213 (). Have control over your agenda? Come by ;-)

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

    On my way to . Very excited. Nevertheless worried about the CO2 emissions. I at least compensated 150% at . Consider doing the same.

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

    Bridging discrete optimization with deep learning. Maybe highly optimized (nondifferentiable) solvers for combinatorial problems will become great again 😍. Differentiation of Blackbox Combinatorial Solvers

    Poništi
  10. proslijedio/la je Tweet
    26. stu 2019.

    Postdoc position available with on "Deep learning techniques for association studies of transcriptome and system dynamics in tissue morphogenesis" in Goettingen

    Poništi
  11. proslijedio/la je Tweet
    1. stu 2019.

    There is a petition to open the SfN meeting to remote attendees to fight the climate crisis. As past program director for SfN, I highly recommend you sign the petition!

    Poništi
  12. proslijedio/la je Tweet
    21. lis 2019.

    Can we trust interpretation of machine-learning models that are good at predicting data? Our preprint on shows that good data prediction and accurate interpretation of the model are not the same.

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    17. lis 2019.

    you know and love ? the excellence cluster " - new perspectives for " is looking for a leader for its ML transfer center, helping to organize interactions with lots of scientific disciplines -

    Poništi
  14. proslijedio/la je Tweet
    30. ruj 2019.

    A small blog post explaining my pledges to save the climate by my personal "air-travel ban" over at

    Poništi
  15. proslijedio/la je Tweet
    26. ruj 2019.

    Come join an excellent environment for neuroscience research. Supportive colleagues. An international community of researchers. Collaboration across the board: from human MEG to mouse 2-photon.

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

    Next attempt to be useful in ML as a mathematician is coming out soon! Differentiating through combinatorial algorithms requires efficiently "inventing" gradients of piecewise constant functions. Here's a visualization of the algorithm.

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    20. ruj 2019.

    Very nice experience at the ! Many thanks to the organizers fom for combining a great scientific event with sustainable practises (no plastic and single use packages, large vegetarian/vegan options)

    Poništi
  18. 17. ruj 2019.

    Great work by colleagues from Göttingen unifying subsampling and coarse-sampling. "A unified picture of neuronal avalanches arises from the understanding of sampling effects"

    Poništi
  19. proslijedio/la je Tweet
    4. ruj 2019.

    We are hiring!📣 Build exciting solutions with us & help shape a dynamic startup from its early days. If you know how to work with common deep learning frameworks & have an entrepreneurial mindset, join us as a Machine Learning Engineer.

    Poništi
  20. proslijedio/la je Tweet
    17. kol 2019.

    Some told me that lab managers are only for bachlor degree holders, but this recruitment aims for a ph.d. with much higher responsibilities, (could be made permanent later), please help spread the word

    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:

    ·