Tweetovi

Blokirali ste korisnika/cu @calabi_and_yau

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

  1. Prikvačeni tweet
    25. stu 2019.

    Last fall I gave a short talk about our Data Science work : "Deep Learning for NLP in Reinsurance" . Made a case for 's Drivetrain approach, which is really great!

    Poništi
  2. proslijedio/la je Tweet
    prije 10 sati

    No one can fool you as easily as you can fool yourself! We must be careful not to believe things simply because we want them to be true.

    Poništi
  3. proslijedio/la je Tweet
    prije 9 sati

    New fastai2 feature in master: Ever forgotten to normalize your inputs properly? A fastai Learner knows what data you use, what model you use, and whether you're pretraining - so it also knows what normalization to use. So now it'll do it for you automatically! (It's optional)

    Poništi
  4. proslijedio/la je Tweet
    4. velj

    I had a lot of fun on the podcast yesterday. Here's a clip of me talking about , hard work and first-principles engineering at Tesla, SpaceX, and Neuralink. Full JRE episode:

    Poništi
  5. proslijedio/la je Tweet
    prije 23 sata
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    prije 23 sata
    Poništi
  7. proslijedio/la je Tweet
    4. velj

    François () is both an independent ML researcher investigating sparse efficient models and... an early angel investor in 🤗 Happy that he agreed to share some of his knowledge and experience on sparse models in a series of posts! First one is here

    Poništi
  8. proslijedio/la je Tweet
    4. velj

    "How to do machine learning efficiently". There's so much to love about this wonderful article.

    Poništi
  9. proslijedio/la je Tweet
    4. velj

    It's official, has hit 100k downloads in just 5 months! 45k just in the last 2 months. If you are still coding for-loops by hand or doing your own distributed training, you should REALLY check out lightning.

    Poništi
  10. proslijedio/la je Tweet
    4. velj
    Poništi
  11. proslijedio/la je Tweet
    31. sij

    Great chatting with . We talked about everything from the early mistakes I made building MOOCs to the challenges of deploying AI systems. Stay tuned for the podcast episode!

    Poništi
  12. proslijedio/la je Tweet
    3. velj

    Help revolutionize the world with full self-driving by joining us at Tesla Autopilot: It is very hard to find other places where AI expertise makes as much of a difference on as big of a problem.

    Poništi
  13. proslijedio/la je Tweet
    3. velj

    The fundamental law of data science & AI: "Your predictions are only as good as your data." For every fancy algorithm you devise, there's some dude with a wagon full of phones running game on you.

    Poništi
  14. proslijedio/la je Tweet
    3. velj

    The 2.4.0 release of transformers is **𝐌𝐀𝐒𝐒𝐈𝐕𝐄** thanks to our amazing community of contributors. 🔥

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

    Every child is a scientist by nature! Children lose their inborn curiosity as they grow up. The important thing is to keep asking questions, keep learning - and doing - new things.

    Poništi
  16. proslijedio/la je Tweet
    3. velj

    Tesla AI recruitment 🔥 “A PhD is definitely not required. All that matters is a deep understanding of AI and ability to implement NNs in a way that is actually useful (latter point is what’s truly hard). Don’t care if you finished high school.”

    Prikaži ovu nit
    Poništi
  17. 3. velj

    With behind us, you can find a piece by @h2o on how Machine Learning can be applied to one of Americans favorite sport 🏈

    Poništi
  18. proslijedio/la je Tweet
    2. velj

    Thread 👇 We’ve also had a difficult time with CuDNN as soon as you want to go beyond a basic LSTM and grab cell states, do -style dropout, etc. Maybe now that has an team, things might get better?

    Poništi
  19. proslijedio/la je Tweet
    3. velj

    Using Named Entity Recognition and and data from Chinese tweets, I built a map of accumulated cases of the . Check out my last blog post and stay tuned for a more interactive web app later:

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    2. velj

    The ultimate test of your knowledge is your capacity to convey it to another.

    Poništi
  21. proslijedio/la je Tweet
    2. velj

    Happy multi-cultural palindrome day! Works whether your preferred date format is MM/DD/YYYY or DD/MM/YYYY or YYYY/MM/DD.

    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:

    ·