jaydeep thik

@jaydeepthik

MSCS at The Ohio State University . ML and DL enthusiast on a mission to make machines learn, think, understand,imagine and to solve the problem of intelligence

India
github.com/jaydeepthik
Vrijeme pridruživanja: svibanj 2014.
2 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @jaydeepthik

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

  1. proslijedio/la je Tweet
    2. sij

    Brains are amazing. Our lab demonstrates that single human layer 2/3 neurons can compute the XOR operation. Never seen before in any neuron in any other species. Out now in . Congrats Albert, Tim  & CO

    840 proslijeđenih tweetova 2.219 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    9. pro 2019.

    At , we care about speed. 75x faster tokenizers. 🤯

    I heard some of you found the tokenizers too slow. I think you are going to love what we are cooking for you
    23 proslijeđena tweeta 178 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    8. pro 2019.

    11 replies 70 proslijeđenih tweetova 428 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    3. pro 2019.

    Gradient descent is hugely controversial in neuroscience. See the ultimate megathread:

    8 replies 27 proslijeđenih tweetova 137 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    8. pro 2019.

    Facebook AI is getting ready to welcome all of you at ! Swing by booth 509 to learn more about cutting-edge research we’re presenting this year. Read more:

    20 proslijeđenih tweetova 169 korisnika označava da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    4. stu 2019.

    loads of ml

    THREAD: There are lots of great educational and entertaining machine learning YouTube channels out there. and I have compiled this list to share some of the best channels that we’ve found.
    Prikaži ovu nit
    1 proslijeđeni tweet 4 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    30. lis 2019.

    It's humbling and inspiring that many big discoveries seem obvious in retrospect. This suggests that there are simple undiscovered ideas, right before our eyes, waiting to be noticed by a mind that's bold enough to look for the obvious.

    40 replies 294 proslijeđena tweeta 1.475 korisnika označava da im se sviđa
    Poništi
  8. 23. lis 2019.

    Bravo !!!!

    2 korisnika označavaju da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    23. lis 2019.

    We are excited to announce the results of our quantum supremacy experiment. Using a fully programmable, 54-qubit processor, called “Sycamore”, we have performed a calculation in 200 seconds that’s infeasible on the fastest supercomputers. Learn more ↓

    838 proslijeđenih tweetova 1.880 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    17. lis 2019.

    Conventional wisdom: slowly decay learning rate (lr) when training deep nets. Empirically, some exotic lr schedules also work, eg cosine. New work with Zhiyuan Li: exponentially increasing lr works too! Experiments + surprising math explanation. See

    17 replies 148 proslijeđenih tweetova 589 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    17. lis 2019.

    What happens in the IT cortex and to the subsequent behavior of non-human primates when you silence visually driven vlPFC neurons? Can deep-nets predict this? Come check out my poster [Tuesday Oct 22ⁿᵈ from 8 am; or Saturday Oct 19ᵗʰ at 6:30 pm @ poster session]

    1 reply 3 proslijeđena tweeta 35 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    14. lis 2019.

    🚀 3.8 has been released! Learn what's new and how to use it at What's your favorite 3.8 feature?

    18 replies 591 proslijeđeni tweet 1.425 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    9. lis 2019.

    Seeing a lot of confusion regarding these two terms in GAN papers lately. Mode Collapse: When a large region of a model's input space maps to a small region around a single (often bad) sample. Mode Dropping: When modes in the data are not represented in the output of the model.

    6 replies 151 proslijeđeni tweet 517 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    6. ruj 2019.

    Thrilled to be able to share what I've been working on for the last year - solving the fundamental equations of quantum mechanics with deep learning!

    35 replies 413 proslijeđenih tweetova 1.607 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    6. ruj 2019.

    In our new blog post, we review how brains replay experiences to strengthen memories, and how researchers use the same principle to train better AI systems:

    192 proslijeđena tweeta 567 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    12. kol 2019.

    Uber built a fake city to test its driver less cars

    This is Uber's fake city
    Uber created the fake city of Almono to test out its driverless cars. Located just outside of Pittsburgh, PA, Almono is the size of 40 football fields.
    50 proslijeđenih tweetova 73 korisnika označavaju da im se sviđa
    Poništi
  17. 7. kol 2019.

    1 korisnik označava da mu se sviđa
    Poništi
  18. proslijedio/la je Tweet
    6. kol 2019.

    Announcing EfficientNet-EdgeTPU, a family of image classification models created using and optimized for use on , that provide real-time performance while achieving the accuracy of much larger, server-side models. Check it out below ↓

    187 proslijeđenih tweetova 497 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    25. srp 2019.

    We’re excited to announce the results of our research collaboration with , applying Population Based Training (PBT) to help make the process of training neural nets in their self-driving cars more effective and efficient.

    6 replies 384 proslijeđena tweeta 1.031 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    17. srp 2019.

    We were so excited last night to show the world what we've been doing for the last two years. If you missed it, you can catch the full recording here:

    508 replies 2.101 proslijeđeni tweet 11.419 korisnika označava da im se sviđa
    Poništi

@jaydeepthik još nije objavio nijedan Tweet.

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:

    ·