Shivam Duggal

@ShivamDuggal4

AI Resident , past

Vrijeme pridruživanja: lipanj 2017.
0 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @ShivamDuggal4

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @ShivamDuggal4

  1. proslijedio/la je Tweet
    3. svi 2019.

    If you're bored and uninspired, get to work, don't wait for inspiration to magically strike. Inspiration isn't something you receive from your surroundings, it's something you make for yourself. It comes from what you choose to think about and what you choose to do.

    27 replies 760 proslijeđenih tweetova 2.716 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    10. tra 2019.

    Left: MIT computer scientist Katie Bouman w/stacks of hard drives of black hole image data. Right: MIT computer scientist Margaret Hamilton w/the code she wrote that helped put a man on the moon. (image credit )

    817 replies 64.247 proslijeđenih tweetova 144.629 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    9. tra 2019.

    Very excited to announce a project 3 years in the making: BLUE, a low-cost, safe, capable robot designed from the ground up with AI in mind. Want BLUE? You can now sign up for priority access here: Learn more here: w/

    8 replies 336 proslijeđenih tweetova 1.080 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    28. ožu 2019.

    FOUR Productivity FEYNMAN- strategies: i) Stop trying to know-it-all. ii) Don't worry about what others are thinking. iii) Don't think about what you want to be, but what you want to do. iv) Have a sense of humor and talk honestly.

    13 replies 1.322 proslijeđena tweeta 3.779 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    30. lis 2018.

    It would be great if your body could store sleep hours, like sleep for 16 hours, than you could stay up for two days without getting tired.

    47 replies 1.812 proslijeđenih tweetova 9.742 korisnika označavaju da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    16. lis 2018.

    Here is the same dynamic RNN implemented in 4 different frameworks (TensorFlow/Keras, MXNet/Gluon, Chainer, PyTorch). Can you tell which is which?

    31 reply 495 proslijeđenih tweetova 1.551 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    26. ruj 2018.

    When you use a 10 layer Deep Neural Network where Logistic Regression would suffice

    87 replies 3.027 proslijeđenih tweetova 9.190 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    25. srp 2018.

    If you cannot explain something in simple terms, you don't understand it.

    30 replies 1.121 proslijeđeni tweet 2.873 korisnika označavaju da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    21. srp 2018.

    FEYNMAN learning strategy in THREE points: 1. Continually ask "Why?" 2. When you learn something, learn it to where you can explain it to a child. 3. Instead of arbitrarily memorizing things, look for the explanation that makes it obvious.

    25 replies 1.985 proslijeđenih tweetova 4.306 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    22. lip 2018.

    Do you often find it cumbersome to track down the best datasets or the state-of-the-art for a particular task in NLP? I've created a resource (a GitHub repo) to make this easier.

    19 replies 466 proslijeđenih tweetova 1.243 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    14. lip 2018.
    Odgovor korisniku/ci

    Doesn't work in bay area though. Once an Uber driver asked me sth similar and I answered as I am doing statistical learning. He then asked what do you think about Hinton's Capsule Networks.

    4 proslijeđena tweeta 40 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    13. lip 2018.

    Texter is a latex symbol retriever. It is developed using which allows an offline version and a much faster prediction time then Detexify. DEMO : CODE :

    17 proslijeđenih tweetova 57 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    10. lip 2018.

    The most successful people I've met: 1. Read constantly 2. Workout daily 3. Are innately curious 4. Have laser focus 5. Believe in themselves 6. Build incredible teams 7. Admit they know very little 8. Constantly work to improve 9. Demand excellence in everything they do

    1.812 replies 11.670 proslijeđenih tweetova 41.669 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    8. lip 2018.

    No matter where you are, there's always room to grow. You came this far, now it would be a shame to just stay there

    189 proslijeđenih tweetova 683 korisnika označavaju da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    4. lip 2018.

    If publishing your paper requires you to select specific ideas, architectures, and hyperparameters according to a fixed validation set, then it's not longer a validation set, it's a training set. And there are no guarantees that the selected ideas will generalize to real data.

    18 proslijeđenih tweetova 102 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    4. lip 2018.

    We're thrilled to announce that we've entered into an acquisition agreement with !

    1.557 replies 8.337 proslijeđenih tweetova 12.621 korisnik označava da mu se sviđa
    Poništi
  17. proslijedio/la je Tweet
    30. svi 2018.

    The most effective engineers I’ve met in my career are those who: - choose the right problems to tackle at the right time - communicate effectively - are humble and have empathy for others

    7 replies 134 proslijeđena tweeta 640 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    31. svi 2018.

    An observation about linear methods in .

    5 replies 77 proslijeđenih tweetova 207 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    28. ožu 2018.

    me trying to read papers (or articles), getting lost in references and not finishing any :S

    19 proslijeđenih tweetova 98 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    16. svi 2018.

    AI and Compute: Our analysis showing that the amount of compute used in the largest AI training runs has had a doubling period of 3.5 months since 2012 (net increase of 300,000x):

    49 replies 477 proslijeđenih tweetova 1.164 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi

@ShivamDuggal4 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:

    ·