K. Rene Traore

@ReneTraore2

Data Scientist & . From Burkina Faso. Account for professional purposes. But opinions are my own.

Munich, Germany
Vrijeme pridruživanja: rujan 2019.

Tweetovi

Blokirali ste korisnika/cu @ReneTraore2

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @ReneTraore2

  1. proslijedio/la je Tweet
    3. velj

    Researchers at our institute in have designed and fabricated an untethered that is actuated through ultrasound. It's amazing that was published in :

    Poništi
  2. proslijedio/la je Tweet
    30. sij

    What's in store for this year? Research into the , , , Tomorrow's Digital Society & more! ✈️🛰💡🚙🌎 At our Annual Press Conference in today, we presented our priorities for 2020

    Poništi
  3. proslijedio/la je Tweet
    28. sij

    You can already try an experimental V3.0 of Stable Baselines with 2 support ;)! The library will be mostly rewritten while keeping the same api. Discussion: Experimental Repo (PPO, TD3): Colab:

    Poništi
  4. proslijedio/la je Tweet
    30. sij

    Amazing: every week I see a paper comparing algorithms using mean performance over *3* seeds ! Yes, ****3**** !!! Please please community, your great ideas will be served better using standard scientific methods!

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

    We are presenting our work "DisCoRL: Continual Reinforcement Learning via Policy Distillation" at the Deep Reinforcement Learning workshop today with T Sun, G Cai, and A "CL for RL" method applicable on real robots!

    Poništi
  6. 3. pro 2019.

    If you are interested in Continual Learning, you should have a look to this - applies not only to Robotics but to other fields as well.

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

    EfficientDet: Scalable and Efficient Object Detection. A new family of object detectors that achieves an order-of-magnitude better efficiency than prior art. +Large scale experiments from Google Brain

    Poništi
  8. 13. stu 2019.

    Taking advantage of unlabelled data via Knowledge Distillation allows to improve SOTA 😃

    Poništi
  9. proslijedio/la je Tweet
    10. stu 2019.

    😊Self-supervised learning opens up a huge opportunity for better utilizing unlabelled data while learning in a supervised learning manner. My latest post covers many interesting ideas of self-supervised learning tasks on images, videos & control problems:

    Poništi
  10. 14. lis 2019.

    About the friendship & characters that 'made Google huge', and probably shaped modern Data Science (e.g Google Search Engine with BigTable & MapReduce, TensorFlow & Google Brain ...). Legendary !

    Poništi
  11. proslijedio/la je Tweet

    Stitch Fix on GitHub: *scipy.linalg.svd(user_likes_matrix)* Stitch Fix on LinkedIn:

    Poništi
  12. proslijedio/la je Tweet
    5. kol 2018.

    Continuous Learning (CL) is built on the idea of learning continuously and adaptively about the external world and enabling the autonomous incremental development of ever more complex skills and knowledge.

    Prikaži ovu nit
    Poništi
  13. 7. lis 2019.

    We merge State Representation Learning, Reinforcement Learning and Continual Learning to learn simple robotic tasks incrementally, and deploy them in real life! Check out our preprint:

    Prikaži ovu nit
    Poništi
  14. 7. lis 2019.

    Excited to share that our work "DisCoRL: Continual Reinforcement Learning via Policy Distillation", with , , T Sun, G. Cai, , has been accepted to the Deep RL Workshop 2019.

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    3. lis 2019.

    You can now edit📝, create🆕, save💾, and move➡️ files and folders📂 through file browser on the left.

    Poništi
  16. proslijedio/la je Tweet

    These short, open-access, must-read papers contain 200 tips to help PhD students and researchers learn the rules of the game: 100 PhD + 100 Research rules of the game. and #PhD#phdchat

    Poništi
  17. proslijedio/la je Tweet

    Overjoyed to announce that I have N papers accepted to the [name of international conference on X]! [no details about the work or coauthors follow]

    Poništi
  18. proslijedio/la je Tweet
    28. ožu 2018.

    Neural architecture search (NAS) is an exciting topic (that allows non-experts to use deep learning in an easier way). To get a better overview, we started to compile a literature list related to NAS. Enjoy!

    Poništi
  19. proslijedio/la je Tweet
    25. srp 2019.

    I am reviewing some CoRL (Conf. on Robot learning) and Humanoids papers (6 papers total). None of them are reporting tests with a real robot (only simulation) => When did the robotics community stop caring about actual robots? these papers should be submitted to SIGGRAPH!

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    30. srp 2019.

    For more context about EfficientNet, check out my earlier tweet:

    Prikaži ovu nit
    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:

    ·