Eric Nalisnick

@eric_nalisnick

Postdoc

Cambridge, England
enalisnick.github.io
Vrijeme pridruživanja: siječanj 2016.
22 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @eric_nalisnick

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

  1. Prikvačeni tweet
    6. pro 2019.

    Indeed, what better way to spend your flight than immersed in 60 pages of all things flow. Happy to hear any feedback (oversights, clarity issues, etc).

    Looking for something to read in your flight to ? Read about Normalizing Flows from our extensive review paper (also with new insights on how to think about and derive new flows) with
    Prikaži ovu nit
    6 proslijeđenih tweetova 69 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    11. pro 2019.

    To conclude the main conference, we'll present two more papers tomorrow -- come find us at the morning poster session!

    Korisnici , , i
    2 proslijeđena tweeta 13 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    8. pro 2019.

    we'll have open-mic sessions to ignite discussions, as well as invited spotlights! First one will be ( & ) talking about prospects and challenges of Inference with check his survey with

    1 reply 3 proslijeđena tweeta 12 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    23. stu 2019.

    The Bayesian Deep Learning workshop website has been updated with accepted papers and schedule

    53 proslijeđena tweeta 274 korisnika označavaju da im se sviđa
    Poništi
  5. 19. ruj 2019.

    Also checkout , , and 's complementary work on batch Bayesian active learning:

    5 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. 19. ruj 2019.

    Interested in Bayesian active learning and/or coresets? We make connections between the two, leading to an efficient algorithm for batch-wise data collection.

    1 reply 3 proslijeđena tweeta 35 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    19. ruj 2019.

    10 papers with authors will appear at in Vancouver, Canada. See below for details.

    1 reply 7 proslijeđenih tweetova 27 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. 26. lip 2019.

    Big thanks to for providing an open source implementation of our Glow CIFAR-10 vs SVHN experiment:

    Attending ? Interested in uncertainty, generative models and out-of-distribution robustness? Check out our poster "Do deep generative models know what they don't know?" this Thursday 430-630pm (Joint work with & Dilan )
    Prikaži ovu nit
    2 proslijeđena tweeta 27 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    16. lip 2019.

    Goodbye ! It was amazing, thank you organisers. See you at in Vienna! Before leaving: Congrats to our group members , , , Jiri Hron, Niki Kilbertus and Francisco Ruiz for being outstanding reviewers (top 5%).

    2 proslijeđena tweeta 17 korisnika označava da im se sviđa
    Poništi
  10. 9. lip 2019.

    #2 Hybrid Models with Deep and Invertible Features: We combine normalizing flows and GLMs to define a deep model that can compute p(y,x) in a single feedforward pass. w/ , , D. Gorur, Paper:

    9 proslijeđenih tweetova 45 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. 9. lip 2019.

    #1 Dropout as a Structured Shrinkage Prior: Mult. noise in NNs (dropout being the Bern. case) induces a scale mixture prior. This decouples dropout's prob interpretation from VI. w/ and P. Smyth Paper: Code:

    1 reply 16 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. 9. lip 2019.

    This week I'll be presenting two papers...

    1 reply 8 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    9. lip 2019.

    We’re excited to be at in Long Beach this week! Our group members will be presenting 12 main conference papers, five workshop papers, and give an invited workshop talk. See the schedule below for more details:

    1 reply 7 proslijeđenih tweetova 34 korisnika označavaju da im se sviđa
    Poništi
  14. 3. lip 2019.

    Visiting Oxford wasn't nearly as bad as all the Cantabrigians said it would be. Here are the slides from my talk at the seminar:

    7 proslijeđenih tweetova 44 korisnika označavaju da im se sviđa
    Poništi
  15. 30. svi 2019.

    Nice paper by Andrew Stirn, , and on formalizing the use of the Kumaraswamy distribution for stick-breaking with reparametrized gradients:

    4 korisnika označavaju da im se sviđa
    Poništi
  16. 28. svi 2019.

    Returning to social media now that the NeurIPS deadline has passed? Give us a follow...

    Hello Twitter! Apologies for the delay in tweets, our social media person has been busy training a Gaussian Process on a few hundred data points 😴😴😴. Follow us for the latest news about our group!
    6 korisnika označava da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    5. ožu 2019.

    Hot off the presses! New work with my fantastic student Belinda Tzen: "Theoretical guarantees for sampling and inference in generative models with latent diffusions" 1/4

    1 reply 13 proslijeđenih tweetova 46 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    18. ožu 2019.

    I apparently have a bit of a reputation as someone who is anti-machine learning or anti-AI when it comes to human research. This is a bit of misrepresentation of my views, and (I'd argue) a misrepresentation of the issues "statistics people" take with AI/ML as a whole. (THREAD)

    7 replies 90 proslijeđenih tweetova 233 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    18. ožu 2019.

    We ( ,, , & myself) are organizing a workshop on "Uncertainty & Robustness in Deep Learning" at . See for more info. Please submit your work (deadline: April 30, 2019) and attend the workshop! :)

    1 reply 34 proslijeđena tweeta 107 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    10. ožu 2019.

    Once you reach a certain age, the future for you is decline leading to extinction. Understandably, you want to believe that the whole world is decaying along with you. It's irritating to hear that most things for most people are getting better. Without *ME*? How dare they!

    247 replies 342 proslijeđena tweeta 2.620 korisnika označava da im se sviđa
    Poništi

@eric_nalisnick još nije objavio nijedan Tweet.

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:

    ·