David Rolnick

@david_rolnick

NSF math postdoc at UPenn, recent MIT PhD: Math for understanding neural nets, machine learning for fighting climate change.

University of Pennsylvania
Vrijeme pridruživanja: siječanj 2015.

Tweetovi

Blokirali ste korisnika/cu @david_rolnick

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

  1. proslijedio/la je Tweet
    5. sij

    We are excited to announce travel grants for our workshop at . Applications can be submitted at through March 3. More information at .

    Poništi
  2. proslijedio/la je Tweet

    Submissions for our ICLR workshop "Tackling Climate Change with Machine Learning" are now open! Papers and Proposals due: Feb 4 Apply to mentor or be mentored on submissions: Jan 14 More details:

    , , i još njih 4
    Poništi
  3. 20. pro 2019.

    Thanks for being a part of the workshop at ! It was great to hear your insights in the panel discussion. Video clip including the first panel: More on the workshop:

    Poništi
  4. proslijedio/la je Tweet

    Our workshop at starts tomorrow at 8:15 am Pacific with an opening keynote by . East Ballroom C for those at NeurIPS, public livestream at:

    Poništi
  5. 10. pro 2019.

    For those at , check out our poster #215 this morning on how "Deep ReLU Networks Have Surprisingly Few Activation Patterns"!

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

    For those attending the UN climate change conference () in Madrid, we are holding a panel on AI and climate change this Wed, Dec 4 (Blue Zone, Chile Pavilion, 15:30-17:00 CET). Featuring , Carla Bromberg, , , , Lynn Kaack,

    Poništi
  7. proslijedio/la je Tweet

    Our workshop "Tackling Climate Change with Machine Learning" has been accepted to ICLR 2020, April 26 in Addis Ababa, Ethiopia. More details and a call for submissions to follow!

    Poništi
  8. proslijedio/la je Tweet

    The schedule for our workshop is out! Keynotes by , Carla Gomes, , Lester Mackey. Spotlights on routing aircraft efficiently, predicting wildfire risks, understanding cloud properties, designing next-gen solar panels, and more.

    Poništi
  9. proslijedio/la je Tweet

    What do you think could help accelerate work in climate change and AI? Datasets, training programs, a startup incubator -- what do you wish existed that would enable meaningful progress?

    Poništi
  10. proslijedio/la je Tweet

    How can help tackle ? Our updated set of recommendations is out, with new applications, graphics, interactive summaries, and background readings/data. Paper: Resources:

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    8. stu 2019.

    Official account for Climate Change AI, facilitating work that tackles climate change with machine learning. Follow for updates on our community and impactful work in this area.

    Poništi
  12. 30. lis 2019.

    Excited to announce the new Climate Change AI discussion forum. For sharing resources and building teams at the intersection of and . All backgrounds welcome.

    Poništi
  13. 25. lis 2019.

    Thanks for having us on the podcast! First episode (w/ , Lynn Kaack, ) on the making of the paper + electricity systems, transportation, buildings & cities, climate prediction. Second episode (w/ , ): tools for individuals & society.

    Poništi
  14. 2. lis 2019.

    In new work with , we reconstruct the architecture, weights, and biases of unknown deep ReLU networks by observing their output. ReLU nets are piecewise linear functions - a lot of info is in the boundaries between linear regions. Full paper:

    Poništi
  15. proslijedio/la je Tweet
    1. lis 2019.

    A group of academic and industry researchers say and can help tackle challenges. Two recipients and Kelly Kochanski are part of this collaborative effort.

    Poništi
  16. 27. ruj 2019.

    “Eye on A.I.” podcast - enjoyed speaking together with about tackling climate change with machine learning. Thanks for having us on the show!

    Poništi
  17. 19. ruj 2019.

    For those , 4-5 pm today, next installment of our discussion series Growing Up in Science - professors chat about their career trajectories and experiences as students. This month w/ . Thanks to ,

    Poništi
  18. 9. ruj 2019.

    “Tackling Climate Change with Machine Learning” is accepting submissions (2-3 pages) through Wednesday! Limited travel grants are available to NeurIPS. 30K in prizes for best submissions. More info at

    Poništi
  19. 4. ruj 2019.

    Our paper "Experience Replay for Continual Learning" accepted to - inspiration from the brain gives start-of-the-art reduction in catastrophic forgetting for deep RL (w/ Greg Wayne, Tim Lillicrap, , , ) Paper:

    Poništi
  20. 3. ruj 2019.

    Looking forward to presenting "Deep ReLU Networks Have Surprisingly Few Activation Patterns” at with . Full paper:

    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:

    ·