Rezultati pretraživanja
  1. 29. lis 2019.

    Learning to Predict Without Looking Ahead: World Models Without Forward Prediction Rather than hardcoding forward prediction, we try to get agents to *learn* that they need to predict the future. Check out our paper!

    Prikaži ovu nit
  2. (6)AI = Amazing Ideas In 2019, we started our work on using AI to track & improve students’ engagement in class, AI CLASS MONITOR. A work accepted in the stream of Watch: What will AI mean to you in 2020? Write and win

    Prikaži ovu nit
  3. Refreshingly honest take on hype cycle around the Neural ODE paper by one of authors presented this year at , which won a best paper award at last year. Video:

  4. 15. pro 2019.

    A highlight for me was 's refreshingly honest talk about the Neural ODEs paper, part of the retrospectives workshop. Check it out !

  5. The MineRL Competition 2019 asked teams to train an AI agent to obtain a diamond in Minecraft. & will host a workshop that takes a closer look at methods used tomorrow. Try the MineRL reinforcement learning environment:

  6. Exciting day tomorrow for those who love Deep RL! Deep RL Workshop (West Exhibition Hall C): -We will start by presenting at 9:00 (also as poster) - Five will follow at 9:30 Full schedule:

    Prikaži ovu nit
  7. A fun little demonstration of the scale of - video of people heading into keynote talk. This is 9 minutes condensed down to 15 seconds, and this is not even close to all the attendees!

  8. 11. pro 2019.

    Check out our poster #143 on general E(2)-Steerable CNNs tomorrow, Thu 10:45AM. Our work solves for the most general isometry-equivariant convolutional mappings and implements a wide range of related work in a unified framework. With

    Prikaži ovu nit
  9. Most eye catching industry booth award at easily goes to . Wish there were more fun robots or live demos around...

  10. 11. pro 2019.

    Preferred Networks proudly co-organized MineRL competition at for sample-efficient reinforcement learning. Please join our winner's presentation in Competition Track Day 2 on Saturday! 9-11AM December 14th @ West 116-117

  11. 10. pro 2019.

    We'll be presenting our work on multiplicative composition policies (MCP) at on Wed 5-7pm, poster #44. Come and checkout a simple method to learn composable motor primitives for a soccer playing T-Trex

  12. 10. pro 2019.

    visualization for arxiv:1902.02476, "A simple baseline for bayesian uncertainty in deep learning.", pca directions, a collab with & , part of the project

  13. IBM Research is at . Stop by and try our tech, or learn more about the work our scientists are featuring ➡️

  14. 8. pro 2019.

    If you like PHATE and neural networks, check out m-PHATE (with and Adam Charles) for visualizing network behavior, to be presented at ! See video:

    Prikaži ovu nit
  15. Hey, I'm at ⓃⓔⓤⓡⒾⓅⓈ 2019 in Vancouver! Come check out the amazing work of competitors in the comp! Excited to award several GPUs from NVIDIA to the winners Sat Dec 14 9:00 AM @ West 116 + 117 w/

    Prikaži ovu nit
  16. 8. pro 2019.

    If you like the Bash and you love , hop over to my demo of Project CLAI (soon to be open-sourced) at the booth and at the demo session. with

    Prikaži ovu nit
  17. 8. pro 2019.

    8:30am Sunday; starts with a bang! admits to the world that he’s a Bayesian! (meme-ready short version: ). :-)

  18. 8. pro 2019.
  19. 6. pro 2019.

    The Artificial Intelligence global community will gather at Canada 8-14 Dec. Our work on using AI to track & improve students’ engagement in class, AI CLASS MONITOR is one of the accepted posters in stream Watch:

  20. 21. stu 2019.

    Neural net training is surprising! Hear why in this talk by yours truly on our LCA paper, to be presented at . Work championed by with and :

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.