Yarin

@yaringal

Associate Professor of Machine Learning, University of Oxford Group Leader

Oxford, England
yarin.co
Vrijeme pridruživanja: veljača 2014.
84 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @yaringal

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

  1. Prikvačeni tweet
    14. lip 2019.

    Really excited to release Bayesian Deep Learning Benchmarks - please share with others who you think might like this, and have a look at the blog/repo/colab: This work was done over a period of a year and a half by many collaborators

    7 replies 395 proslijeđenih tweetova 1.143 korisnika označavaju da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    2. velj

    Manipulating content you consume has immense impact on wellbeing and beliefs. Yet we outsource this content to . explaining the risks

    5 proslijeđenih tweetova 15 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    2. velj

    Was a real joy to give this talk ☺️

    Manipulating content you consume has immense impact on wellbeing and beliefs. Yet we outsource this content to . explaining the risks
    2 proslijeđena tweeta 58 korisnika označava da im se sviđa
    Poništi
  4. 27. sij

    two lectureships in ML at CBL in Cambridge (or CV at MIL)

    Two great positions available in Cambridge Information Engineering
    1 reply 2 proslijeđena tweeta 21 korisnik označava da mu se sviđa
    Poništi
  5. proslijedio/la je Tweet
    26. sij

    My neighbours! Don't eat them. Have chicken or bacon instead .. @ Richmond, North Yorkshire

    2 proslijeđena tweeta 10 korisnika označava da im se sviđa
    Poništi
  6. 24. sij

    Thanks ! The students love these

    1 proslijeđeni tweet 10 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. 17. sij

    Interesting:

    [News] Preferred Networks releases Optuna v1.0, the first major version of the open-source hyperparameter optimization framework for machine learning. Optimize your optimization.
    9 proslijeđenih tweetova 31 korisnik označava da mu se sviđa
    Poništi
  8. proslijedio/la je Tweet
    13. sij

    AWS accidentally sent me their email newsletter template, and it's kinda great. cc ;)

    1.606 proslijeđenih tweetova 6.665 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    14. sij

    I wrote this self-contained, 150 line script that trains a ResNet-18 to ~94% accuracy on CIFAR-10. Useful for obtaining a strong baseline with minimal tricks. Uses / Torchvision: 👉

    1 reply 34 proslijeđena tweeta 226 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    7. sij

    I'm excited to share that I have joined Imperial College London as a lecturer (asst prof)! I'm convinced it will be a great environment to continue working on GPs, Bayesian Deep Learning, and model-based RL. Do get in touch if you're interested joining to do a PhD!

    55 replies 46 proslijeđenih tweetova 649 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    24. pro 2019.

    A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks by Angelos Filos et al. including

    17 proslijeđenih tweetova 40 korisnika označava da im se sviđa
    Poništi
  12. 30. pro 2019.

    Contributions from readers keep Wikipedia independent. It takes 2min to donate

    3 proslijeđena tweeta 32 korisnika označavaju da im se sviđa
    Poništi
  13. 27. pro 2019.

    Very well put . "BDL is gaining visibility because we are making progress. We shouldn’t discourage these efforts. If we are shying away from an approximate Bayesian approach because of some challenge or imperfection, we should always ask, “what’s the alternative”?"

    Bayesian methods are *especially* compelling for deep neural networks. The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. This difference will be greatest for underspecified models like DNNs. 1/18
    Prikaži ovu nit
    4 proslijeđena tweeta 64 korisnika označavaju da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    22. pro 2019.
    Odgovor korisnicima

    Similarly Radford Neal's PhD thesis makes a strong argument for taking a Bayesian approach to NNs ().

    1 reply 16 proslijeđenih tweetova 99 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    22. pro 2019.
    Odgovor korisniku/ci

    David Mackay did a great job of outlining the reasoning for taking a Bayesian approach to neural networks in the early 90s and I think all his points still ring true:

    1 reply 22 proslijeđena tweeta 159 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    20. pro 2019.

    Oxford CS is hiring a Departmental Lecturer in machine learning:

    15 proslijeđenih tweetova 44 korisnika označavaju da im se sviđa
    Poništi
  17. 20. pro 2019.

    VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning [4/4]

    8 proslijeđenih tweetova 15 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. 20. pro 2019.

    Gradient l1 Regularization for Quantization Robustness [3/4]

    1 reply 2 proslijeđena tweeta 7 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. 20. pro 2019.

    BayesOpt Adversarial Attack [2/4]

    1 reply 3 proslijeđena tweeta 10 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. 20. pro 2019.

    Congratulations to Robin Ru, , and for their ICLR accepted papers: [1/4]

    1 reply 1 proslijeđeni tweet 25 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  21. proslijedio/la je Tweet
    19. pro 2019.

    At I spoke at the Bayesian Deep Learning workshop on the central limit theory for multiple hidden layers and then on the panel. Slides and video here:

    1 reply 37 proslijeđenih tweetova 135 korisnika označava da im se sviđa
    Poništi

@yaringal 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:

    ·