Soumith ChintalaOvjeren akaunt

@soumithchintala

I ❤ research -- multi-modal world models, robots. I think deeply about lowering the barrier to use A.I. I co-created and lead PyTorch at Facebook A.I.

New York City
Vrijeme pridruživanja: rujan 2009.

Tweetovi

Blokirali ste korisnika/cu @soumithchintala

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

  1. proslijedio/la je Tweet
    27. sij

    I am super excited to join today, leading the software team that builds tooling to enable 'silicon at the speed of software'. Chip design is challenging, and needs open tools that are well designed, easy to use, and state of the art. More at:

    Poništi
  2. Super excited to welcome Robert, Ross and team! We share a vision of making researchers’ life more efficient, neutrally working for the entire scientific community. and are orthogonal in that way. Let’s see what we brew together!

    Poništi
  3. I meant :)

    Prikaži ovu nit
    Poništi
  4. The is only the first. We will be writing more papers on , on v1.0 headed by @dzhugakov and many other pioneers, detailed papers on the JIT compiler headed by and team, on distributed pytorch, etc.

    Prikaži ovu nit
    Poništi
  5. This one is to all of us from around the world who in late 2016 to mid 2017 shaped the project, from the (Lua)Torch community to new core contributors, who baked the open-source cake on days, nights and weekends!

    Prikaži ovu nit
    Poništi
  6. The first full paper on after 3 years of development. It describes our goals, design principles, technical details uptil v0.4 Catch the poster at Authored by , et. al.

    Prikaži ovu nit
    Poništi
  7. Super excited to welcome the PFN team to the community. With Chainer, CuPy, Optuna, MNCore, their innovations need no introduction. The community is going to get even more fun! :)

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

    Our new paper, Deep Learning for Symbolic Mathematics, is now on arXiv We added *a lot* of new results compared to the original submission. With (1/7)

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    13. stu 2019.

    Almost incredible : ! physicists discover new general relationship between eigenvectors and eigenvalues of the minor ! , Terence Tao checks, and does three different proofs within two hours. 🔥

    Poništi
  10. I was really looking forward to come to Khipu, but at the last minute, I'm having to drop out. I damaged my passport, and getting a new passport is taking longer than expected. Sorry about this, and thanks a lot to the organizers for being very patient with me.

    Poništi
  11. Famous person claims: "AI is solved" People: "hell no! we need to call it AGI now". Famous person will claim: "AGI is solved" People: "Arghhhhhi!!!!"

    Poništi
  12. Learning the sense of smell, as well as mapping them onto continuous spaces. Exciting investments and initial research by Alex Wiltschko & team at Google

    Poništi
  13. proslijedio/la je Tweet
    23. lis 2019.

    Pretty good article discussing 's Rubik's Cube result: This is what good criticism looks like, unlike most of the critical tweets mentioned in this article. Good work and .

    Poništi
  14. Grasping and manipulation is one of the hardest problems in making practical consumer robotics work. Good stuff from and team at OpenAI making progress in this direction!

    Poništi
  15. proslijedio/la je Tweet

    It was great to see the posters, on Funsor, learn2learn, torchmeta, Lightning, Ignite and many more ideas and packages. New ideas push the field forward like nothing else. I hope to see this spirit for years to come. (3/x)

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet

    We've focused as a community to promote innovation above everything else, with little space for ego. We were built upon the ideas of many giants before us from Lush, Torch, Chainer, Autograd and we are empowered by many ideas from around us such as Jax, Julia, S4TF. (2/x)

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet

    Mainstream DL Frameworks have consolidated around PyTorch and TensorFlow, but more centrally around a single philosophical direction, and this is very bad. I hope to again see brutal competition of ideas. Let's not get too comfortable with the status quo. (4/x)

    Prikaži ovu nit
    Poništi
  18. Mainstream DL Frameworks have consolidated around PyTorch and TensorFlow, but more centrally around a single philosophical direction, and this is very bad. I hope to again see brutal competition of ideas. Let's not get too comfortable with the status quo. (4/x)

    Prikaži ovu nit
    Poništi
  19. It was great to see the posters, on Funsor, learn2learn, torchmeta, Lightning, Ignite and many more ideas and packages. New ideas push the field forward like nothing else. I hope to see this spirit for years to come. (3/x)

    Prikaži ovu nit
    Poništi
  20. We've focused as a community to promote innovation above everything else, with little space for ego. We were built upon the ideas of many giants before us from Lush, Torch, Chainer, Autograd and we are empowered by many ideas from around us such as Jax, Julia, S4TF. (2/x)

    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:

    ·