Yee Whye Teh

@yeewhye

Professor of Statistical Machine Learning at , and Research Scientist at . All opinions are my own.

Oxford, England
Vrijeme pridruživanja: siječanj 2017.

Tweetovi

Blokirali ste korisnika/cu @yeewhye

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

  1. 28. sij

    Stats and ML folks: for KL[q||p], should one say:

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    13. sij

    Follow the livestream of our Turing Institute workshop on 'Statistics and Computation' -

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    10. sij

    PhD opening at on machine learning for climate science . Project is a part of the () Marie Curie Innovative Training Network funded by . Apply at (deadline Feb 3).

    Poništi
  4. proslijedio/la je Tweet
    7. sij

    Thrilled that our paper on gradient driven experimental design w and Martin Jankowiak was accepted to !

    Poništi
  5. 6. sij

    Deadline for applications is in 2 days (Jan 8)! Contact myself or if you are interested and have some questions. Note that these are independent positions allowing the fellow to develop their own research vision and academic profile.

    Poništi
  6. 6. sij

    . 2020 World Meeting to be held in Kunming, China. Call for contributed talks and posters deadline Jan 15, and junior researcher travel award application deadline Jan 31.

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

    Happy to announce this has been accepted to ICLR 2020! See you all in Ethiopia.

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

    Really pleased that our paper "Multiplicative Interactions and Where to Find Them" was accepted to . We present a unifying picture of several different neural net architectural motifs, that all involve multiplicative interactions... 1/3

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    20. pro 2019.

    Really happy and a lovely early-Christmas present that our paper "Multiplicative Interactions and Where to Find Them" was accepted to . We analyse such interactions, unify different forms (eg hypernets, gating), and encourage you to use more of them! 1/2

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

    I will be giving a Contributed Talk at the Bayesian Deep Learning workshop at at 8:25am today. Stop by if you're interested in function-space perspectives on DNN training dynamics! Paper:

    Poništi
  11. proslijedio/la je Tweet
    11. pro 2019.

    New ELLIS unit brings together experts from , and to shape how machine learning and artificial intelligence will change the world.

    Poništi
  12. 11. pro 2019.

    Proud to be part of Oxford’s vibrant and diverse AI/ML community and part of .

    Poništi
  13. proslijedio/la je Tweet

    We'll be presenting our work today at . Please come along and ask questions :-)

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

    will be presenting our spotlight "Variational Bayesian Optimal Experimental Design" at 4.40pm in West Ballroom C and poster #173. In it, we show how the variational methods can sidestep the double intractability of the expected information gain

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    10. pro 2019.

    Presenting my work w/ & on optimal experimental design today ! Spotlight 4:40pm West Ballroom C

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

    Very excited to present our Poincaré VAE !! Had fun working with and ! Will be from 10.45am at East exhibition hall B + C #109 Check out the just updated paper and code!

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

    meet-up this week :) we are streaming events from neurips and there is local unconference and talks. Join us! Thanks to organisers , sponsors !

    Prikaži ovu nit
    Poništi
  18. 6. pro 2019.

    Great work by . State of the art results on miniImageNet and tieredImageNet.

    Poništi
  19. 29. stu 2019.

    Thank you all! It was great fun chatting with students over the last two weeks. It's been a very positive experience! I wrote up some reflections here:

    Poništi
  20. proslijedio/la je Tweet
    27. stu 2019.

    We've updated our paper on Continual Learning with Gaussian Processes with some new ideas on task-boundary detection and additional ablation studies around inducing point optimisation:

    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:

    ·