Search results
  1. 17 Dec 2019

    At , talking to a guy from DeepMind about how I can't reproduce their results because it's so resource intensive. "It's not too bad actually, we only use 16 GPUs, it's not like we use a cluster of TPUs or anything."

  2. 15 Dec 2019

    What a week 🧠🤓💻! I loved meeting so many of you at - the ML community is truly wonderful. Checkout all my collected visual notes ✍️ & feel free to share:

  3. 14 Dec 2019

    A first for me at a conference: more invited talks by women named Susan than any other category...

  4. 17 Dec 2019

    One theme I noticed at was the need for the ML community to move beyond our narrow focus on prediction. I heard this in 3 very different talks. [Thread]

    Show this thread
  5. 14 Dec 2019

    Machine Learning and the Physical Sciences will live stream

  6. People View all

  7. 16 Dec 2019

    This paper had the biggest subjective "wow" factor for me at : "Deep Set Prediction Networks" by Yan Zhang, Jonathon Hare, Adam Prügel-Bennett . The idea is very simple, and yet I find it mind-blowing.

    Show this thread
  8. 13 Dec 2019

    Graph representation learning is the most popular workshop of the day at . Amazing how far the field has advanced. I did not imagine so many people would get into this when I started working on graph neural nets back in 2015 during an internship. Time flies...

  9. I had a great time presenting my work on imitation from observation at WIML! Here are links to my slides and video :) Slides: Video (starts around 8 mins):

  10. 31 Dec 2019

    Videos of all the great talks from the workshop are now available on the webpage, along with the accepted papers!

  11. 18 Dec 2019

    Neural networks grown and self-organized by noise Inspired by the development of the mammalian visual system, they propose an way to grow and self-organize a retinotopic pooling architecture that behaves like CNNs. Found this weird work at :

    Show this thread
  12. 14 Dec 2019

    is sadly coming to an end and I just wanted to remark on how great the venue is: Canada Place is remarkably well-located, the convention center is walkable to so much good stuff in the city. I enjoy that we get to mingle with locals that take evening strolls here.

    Show this thread
  13. 18 Dec 2019

    My AI art online gallery for 2019 is finally live 🎉 🎉🎉 Check out all the art, music and design projects submitted to our Workshop😍

  14. 19 Dec 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:

  15. I had a great time at the Bayesian Deep Learning Workshop! My talk on "Using Loss Surface Geometry for Practical Bayesian Deep Learning" starts at 6m40s:

  16. And we should not back away from challenges. I present some of these views in my talk at the Bayesian Deep Learning Workshop, starting at 6m40s: 18/18

    Show this thread
  17. 16 Dec 2019

    My invited talk, "Agency + Automation: Designing Artificial Intelligence into Interactive Systems" is online here:

    Show this thread
  18. 17 Dec 2019

    Want to catch up on some latest Deep RL work? Here is a zip file with all the camera-ready papers from the Deep RL Workshop!

  19. EPIC brainpower devoted to AI for . Your work is not over when your paper is published. Success metric should be CO2 sequestered, not papers published. & success depends on close collab with climate experts & broader society outside of ML

    Show this thread
  20. Uploaded my slides from this morning's talk at Robot Learning workshop

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.