George Ho

@_eigenfoo

Researcher/data scientist . Core developer . Bayesian modelling, machine learning and coffee.

New York, NY
eigenfoo.xyz
Vrijeme pridruživanja: svibanj 2017.
29 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @_eigenfoo

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

  1. Prikvačeni tweet
    30. ruj 2019.

    New post! What even is a probabilistic programming framework, how are they structured, and how are the popular open source ones organized?

    6 replies 26 proslijeđenih tweetova 110 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    31. sij

    I've been looking for a correct definition of p values in textbooks... and no wonder everyone has trouble with this. Most of the definitions are straight up wrong. Here follows a list of incorrect examples:

    27 replies 185 proslijeđenih tweetova 588 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  3. 29. sij

    Textbook authors have the best words.

    1 reply 1 korisnik označava da mu se sviđa
    Poništi
  4. 28. sij

    Bash is an interesting language

    Odgovor korisniku/ci @LucyDavinhart
    Always threw me for ages before I realised that '[' is just a program (technically usually a built-in, but whatever) that requires its last argument to be ']' 😆
    1 reply 1 korisnik označava da mu se sviđa
    Poništi
  5. proslijedio/la je Tweet
    28. sij

    +, Σ, and ∫ are just different evolutions of the same Pokémon

    2.785 proslijeđenih tweetova 10.090 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    24. sij

    Why do we love Twitter? Some random bozo has been fighting a Fields Medal winner about math for 2 months now and there’s no end in sight.

    Odgovor korisnicima @Rey_Skywalker8 @johncarlosbaez i sljedećem broju korisnika: 6
    Not being a theoretical physicist, I don't know how to treat a positive integer as infinitesimal, so I'll just have to hope for the best when it comes to that last condition.
    12 replies 134 proslijeđena tweeta 496 korisnika označava da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    24. sij

    A non-standard review of MCMC methods by Christian Robert and Wu Changye. "Non-standard" in that is augmented with questions found on Cross-validated

    34 proslijeđena tweeta 137 korisnika označava da im se sviđa
    Poništi
  8. 23. sij

    Minimum likelihood methods

    10 korisnika označava da im se sviđa
    Poništi
  9. 22. sij

    Every time I buy a new laptop peripheral I feel like my quality of life goes up. I never realized how much I was straining to read the text on my laptop screen.

    Poništi
  10. proslijedio/la je Tweet
    19. sij

    I believe that most criticism of priors stems from ignorance and reluctance to do the hard work. You can start with this and references therein: - Paper: - This post by : 👏Bayesian👏methods👏are👏not👏magical👏

    1 reply 20 proslijeđenih tweetova 67 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    16. sij

    We badly need more diversity in open-source scientific software. If you identify as female/non-binary, my messages are open if you want to chat about how to get involved with open-source (in particular Python for science / Pydata). Open-source dev is great for acquiring skills!

    15 replies 160 proslijeđenih tweetova 350 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    6. sij

    Episode 2 of the Deep Dive with Travis Oliphant : The past, present and future of PyData. We dive into the history of NumPy and his most recent endeavours at . Hope you enjoy!

    1 reply 10 proslijeđenih tweetova 40 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    6. sij

    I'm updating all of my course material -- did I mention that I'm hosting a course next month, 😉 -- and I enjoyed this new figure.

    1 reply 3 proslijeđena tweeta 34 korisnika označavaju da im se sviđa
    Poništi
  14. 6. sij

    Bayesian Yodeling

    Alter one letter of a concept in your discipline. I'll go first. Dank Matter
    Prikaži ovu nit
    8 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    5. sij

    Blog post: Poisson distributions, gamma distributions, and Poisson processes: (Some more friendly neighborhood distributions)

    22 proslijeđena tweeta 96 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    3. sij

    New year, new post: support your data science team with glorious, grandiose books!

    14 proslijeđenih tweetova 45 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. 31. pro 2019.

    Another year, another commit to increment the years in all my Apache 2.0 licenses 😛

    2 korisnika označavaju da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    29. pro 2019.

    For the most part, "it was in a good journal" and "it was done by a good person/group" is irrelevant information.

    1 reply 8 proslijeđenih tweetova 27 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. 28. pro 2019.

    It turns out he is not kidding.

    2000 words of main text, 4000 words of math in the appendix. 🤔
    3 korisnika označavaju da im se sviđa
    Poništi
  20. 28. pro 2019.

    Interesting take on how Google manages tech debt for ML projects: It's slightly upsetting that most of the suggested solutions are organization/infrastructural, but I guess that's par for the course.

    1 proslijeđeni tweet 1 korisnik označava da mu se sviđa
    Poništi
  21. proslijedio/la je Tweet
    21. pro 2019.

    Controversial opinion: Bayesian NNs make no sense. You only want to use Bayes rule if you have a reasonable prior of what the parameters should be. Nobody knows what is encoded by any prior over the weights of a NN. So why would we use such a prior? 1/4

    31 reply 122 proslijeđena tweeta 675 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi

@_eigenfoo 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:

    ·