Tweetovi

Blokirali ste korisnika/cu @filangelos

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

  1. Prikvačeni tweet
    7. ruj 2019.

    Consider submitting your work to our workshop on "Emergent Communication: Towards Natural Language"! The deadline is on **Sunday September 15th**. Authors of accepted papers will get access to a pool of specially reserved tickets! 🤖📡🌊🎰

    Poništi
  2. proslijedio/la je Tweet
    30. sij

    02/02/2020 is the only date in our lifetimes — and the 1st since 11/11/1111 — to be palindromic across the World, in whatever date format you choose.

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

    Poništi
  4. proslijedio/la je Tweet
    22. sij

    New results on non-stochastic control without knowing the system! joint work with and Karan Singh. You may notice the name is a tribute to one of my favorite papers of all times by Auer, Cesa-Bianchi, Freund and Schapire (a must read!)

    Poništi
  5. proslijedio/la je Tweet
    16. sij

    How can we predict and control the collective behaviour of artificial agents? Classical game theory isn't much help when there are >2 agents. In our paper, we find markets impose useful structure on interactions between gradient-based learners:

    Poništi
  6. 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

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

    Very happy to be named one of MIT Technology Review Europe's 35 under 35. Many thanks to all my collaborators over the years!

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

    presenting BDL benchmarks from diabetic retinopathy at the BDL workshop high-res medical images with uncertainty-driven real-world tasks. Easy API.

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

    We'll be demoing our Hanabi AI at the Emergent Communication Workshop on Saturday and giving a talk on it at 2:45! I'm also at NeurIPS for the whole week. If you are interested in multi-agent RL, I'm happy to talk!

    Poništi
  10. proslijedio/la je Tweet

    Interested in active learning? Do you want to acquire diverse batches of data instead of single datapoints? Learn about our approach BatchBALD at 10:45, at board #1 at ! , and me are looking forward to chat!

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

    Big news: Latent Logic, which I co-founded in 2017, has been acquired by (formerly Google's Self-Driving Car Project). We’ll be staying in Oxford as part of Waymo Research and will become their first European engineering hub. Thanks to the team for all their hard work!

    Poništi
  12. proslijedio/la je Tweet
    4. pro 2019.

    We have today released SafeLife – a reinforcement learning environment that tests the safety of reinforcement learning agents and the algorithms that train them. SafeLife explores the side effects of in complex environments:

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    21. lis 2019.

    Excited to share our work: collaboration requires understanding! In Overcooked, self-play doesn't gel with humans: it expects them to play like itself. (1/4) Demo: Blog: Paper: Code:

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    5. lis 2019.

    Check out this amazing repository of ML and DL courses:

    Poništi
  15. proslijedio/la je Tweet
    30. ruj 2019.

    The Paths Perspective on Value Learning — A new Distill article by and .

    Poništi
  16. proslijedio/la je Tweet
    16. ruj 2019.

    Last call for submissions to Emergent Communication workshop ! Deadline extended to Sun Sep 22 midnight! Authors of selected papers get access to reserved tickets for attending the whole conference! 🤖☎️🤖

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    9. ruj 2019.

    No Press Diplomacy: Modeling Multi-Agent Gameplay Diplomacy is a 7-player, non-cooperative game, where agents acquire resources through a mix of teamwork and betrayal. They train agents to play a version with no explicit communications between players.

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    8. ruj 2019.

    Welcome to who has joined as a part-time senior postdoc!

    Poništi
  19. proslijedio/la je Tweet
    7. ruj 2019.

    Since PhD application season is coming up soon just want to plug ! If you want to apply but are feeling uncertain or just want to chat with a present student hit me up! ☺️

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet

    It is by logic we prove. It is by intuition we discover. -Henri Poincaré

    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:

    ·