Tweetovi

Blokirali ste korisnika/cu @tataudat

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

  1. proslijedio/la je Tweet
    20. sij

    Behold the Datasaurus Dozen. New video featuring and a mention of 's book club.

    Poništi
  2. 23. sij
    Poništi
  3. proslijedio/la je Tweet
    20. pro 2019.

    *Grumpy Chris:* One of my biggest research gripes is people boiling the world down into a couple summary statistic numbers and feeling like that somehow made things more rigorous.

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

    In 2020, we will celebrate that many of the basic ideas behind the Deep Learning Revolution were published three decades ago within fewer than 12 months in our "Annus Mirabilis" 1990-1991:

    Poništi
  5. proslijedio/la je Tweet
    18. stu 2019.

    The Sunray solved *A* problem. It had things it did better than the alternatives that existed at the time. It was made with *A* user in mind, even if that user (Sun Microsystems employees) were the same people making the Sunray. There was *someone*— me, in 2004— it was great for.

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    30. kol 2019.
    Poništi
  7. proslijedio/la je Tweet

    Series: the 20 most tactically interesting teams of the 2010s. One per week on .

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    15. stu 2019.

    Some of the smartest people I know are leaving AI research for engineering/neuroscience. Their reasons? 1. We need to understand how humans learn to teach machines to learn. 2. Research should be hypothesis -> experiments, but AI research rn is experiments -> justifying results.

    Poništi
  9. proslijedio/la je Tweet
    28. lis 2019.
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet

    The equal sign forms the bedrock of mathematics. Some mathematicians think it needs to be replaced.

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

    Often times, when you'd like to find out best language practices, you go to the standard library. Weirdly enough, with Rust, I mostly see a bunch of "unsafe" there. Even for something as simple as linked list. Anyone can clarify why?

    Poništi
  12. proslijedio/la je Tweet
    30. kol 2019.

    why are all the violin concertos in the key of D? Full video ➡️

    Poništi
  13. proslijedio/la je Tweet
    5. ruj 2019.
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    Odgovor korisnicima i sljedećem broju korisnika:

    Right-- the goal of default kwargs is not to reduce the amount of typing people do, it's to run the way you think it does based on the name. People get this twisted because it's similar, but you can run through hypothetical code examples to see this.

    Poništi
  15. proslijedio/la je Tweet

    By default, logistic regression in scikit-learn runs w L2 regularization on and defaulting to magic number C=1.0. How many millions of ML/stats/data-mining papers have been written by authors who didn't report (& honestly didn't think they were) using regularization?

    Poništi
  16. proslijedio/la je Tweet
    1. ruj 2019.

    Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective Review paper that aims to shed lights on the importance of dynamics and optimal control when developing deep learning theory.

    Poništi
  17. proslijedio/la je Tweet
    30. kol 2019.

    Facebook scans system libraries from their Android app user’s phone in the background and uploads them to their server This is called "Global Library Collector" at Facebook, known as "GLC" in app’s code It periodically uploads metadata of system libraries to the server

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    23. kol 2019.

    Looking back over the year, the one paper that gave me the best "aha" moment was... Reconciling Modern Machine Learning and the Bias-Variance Tradeoff: The "bias-variance" you knew was just the first piece of the story!

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    21. kol 2019.

    today i learned that Python rounds `float` values by converting them to a string with snprintf and then back via strtod, and now i'm sad.

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    13. srp 2019.
    Odgovor korisnicima i sljedećem broju korisnika:

    Less: ways of computing p-values, hypothesis testing, fuss over whether to divide by n or n-1 in sample var, tedious calculations More: thinking about data quality, sampling, likelihood, bias-variance tradeoff, simulation, visualization, discussion of common misconceptions

    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:

    ·