Rezultati pretraživanja
  1. 17. pro 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. pro 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. 17. pro 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]

    Prikaži ovu nit
  4. 14. pro 2019.

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

  5. 2. velj

    “100x faster Hyperparameter Search Framework with Pyspark” by Rahul Agarwal

  6. 2. velj
  7. 1. velj

    Good time to remind about this paper from the : "Avoiding a Tragedy of the Commons in the Peer Review Process"

    Prikaži ovu nit
  8. 1. velj
  9. 1. velj
  10. 1. velj

    I just came across these notes on -> 70 pages of research summaries. Thanks to these notes I discovered work on successor representations and state uncertainty.

  11. 31. sij

    "Self-Driving Research in Review: NeurIPS 2019" – short reviews of papers from Machine Learning for Autonomous Driving Workshop and main conference by and from

  12. 29. sij

    Nuria Oliver , renowned AI researcher & board member shared ELLIS' mission & new initiative announced at to retain AI talent in Europe. Check out interview & podcast

  13. 29. sij

    Reminder to join us on Monday night at 6pm Eastern to learn about and why conferences rule (and how to capitalize on the experience) from .

  14. 28. sij

    If you weren't able to make it to , head over to our blog for a recap of our favorite self-driving-related papers from the conference.

  15. ■ Research Blog 公開 ■ 先月カナダで行われた の国際学会 に関する 参加報告レポートを公開! ワークショップとメンタリングセッションで AILab研究員が行った3件の研究発表の詳細に加え、 今回の会議の研究動向をご紹介しています📝

  16. 26. pro 2019.

    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

    Prikaži ovu nit
  17. 23. pro 2019.

    Was told this was one of the best talks at , and can see why. Grounded discussion on exploration in RL, pre-2015 research, casting meta-RL as Bayes adaptive MDPs, and a very strong meme game 💯

  18. 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:

  19. Reflecting on . Great meeting as usual, but the AI community is maturing, which felt bittersweet. Bitter because:

    Prikaži ovu nit

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.