Rezultati pretraživanja
  1. 31. svi 2019.

    PyMC 3.7 is out, and it features a new way to manage your data within models.

    29 proslijeđenih tweetova 91 korisnik označava da mu se sviđa
  2. 21. pro 2018.

    3.6 released! This release comes with new features and bugfixes. The main highlight is our shiny new website courtesy of . This will also be the last Python 2 compatible release. Update via pip or conda-forge.

    26 proslijeđenih tweetova 64 korisnika označavaju da im se sviđa
  3. 23. sij

    It took 5 years from scratch to publishing. Finally, also the paper about BEAT is published in SRL: Find the code here: Powered by . Cudos also to the great support of the dev-team.

    21 proslijeđeni tweet 70 korisnika označava da im se sviđa
  4. 17. svi 2018.

    The devs are frequently asked about what's going to happen to the project now that Theano is winding down. Here is a summary of where things are headed.

    1 reply 18 proslijeđenih tweetova 45 korisnika označava da im se sviđa
  5. 12. srp 2019.

    With & we're porting to the end-of-chapter exercises of 's wonderful book, Statistical Rethinking. There are already 4 chapters online, and more to come 😉 Check it out & give us a hand if you want 😊 👉

    17 proslijeđenih tweetova 58 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
  6. 2. stu 2018.

    Slides for my 2PM talk "The Hamiltonian Monte Carlo Revolution is Open Source - Probabilistic Programming with " at

    1 reply 31 proslijeđeni tweet 93 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
  7. 22. lis 2019.

    Do you have seismic and geodetic (InSAR and GNSS) data, but no code yet to do a joint Bayesian deformation source parameter estimation? Checkout BEAT (Bayesian Earthquake Analysis Tool)!

    1 reply 32 proslijeđena tweeta 72 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
  8. 5. pro 2018.

    I've been tracking my steps for several months. Somewhere along the line, I got a puppy. Can Bayesian inference (via ) help me identify the day she arrived?

    6 replies 16 proslijeđenih tweetova 70 korisnika označava da im se sviđa
  9. 14. stu 2019.

    Great (comprehensively updated) post by on dealing with and detecting outliers in GLMs with

    1 reply 20 proslijeđenih tweetova 65 korisnika označava da im se sviđa
  10. 29. sij 2018.

    It's happening! Slowly porting Bayesian delay discounting analysis from Matlab to Python & . Will also extend to general Delayed and Risky Choice (DARC) tasks. Not ready for use, but taking the scary step of developing in the open

    1 reply 13 proslijeđenih tweetova 43 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
  11. 4. lis 2018.

    We have officially released ArviZ - Exploratory analysis of Bayesian models in Python. Works with , , , and .

    1 reply 24 proslijeđena tweeta 63 korisnika označavaju da im se sviđa
  12. 9. lis 2018.

    skpro is a supervised framework that allows for probabilistic forecasting within a unified interface with the goal to make model assessment and comparison fair, domain-agnostic and approachable. integration:

    27 proslijeđenih tweetova 91 korisnik označava da mu se sviđa
  13. 28. ruj 2018.

    Many log CDFs merged into : These allow censoring of distributions. Thanks to domenzain for the contribution!

    7 proslijeđenih tweetova 23 korisnika označavaju da im se sviđa
  14. 18. srp 2018.

    TIL that volunteering to write docs on something you know nothing about is a great way to learn! docs now have more survival analysis stuff 😃

    1 reply 8 proslijeđenih tweetova 43 korisnika označavaju da im se sviđa
  15. 11. lis 2018.

    I just pushed another blogpost in [what is turning out to be] a series about learning how to use . This time: how to learn the off-diagonal elements of the mass matrix. Comments welcome!

    10 proslijeđenih tweetova 49 korisnika označava da im se sviđa
  16. 1. pro 2019.

    What happens behind-the-scenes when you hit 's Inference Button? I dug in to understand it more deeply. Hint: doesn't happen here; instead, it's all glued by one equation.

    92 proslijeđena tweeta 237 korisnika označava da im se sviđa
  17. 19. ruj 2019.

    I have launched the ! Check out Ep1 with where we talk about , , , and baseball analytics It's supposed to be a conversation-based show on more advanced topics, let me know what you think!

    9 replies 89 proslijeđenih tweetova 294 korisnika označavaju da im se sviđa
  18. 20. velj 2019.

    Re-worked my archetypal data analysis workflow to use - a truly transformational package and a LOT more than pretty Bayesian plots - awesome

    1 reply 20 proslijeđenih tweetova 66 korisnika označava da im se sviđa
  19. 16. svi 2018.

    Great to welcome who has come to share his knowledge with our guys in a 2 day workshop on Bayesian statistical modeling. Stay tuned, our Jupyter notebooks and an AV recording of the entire session coming soon.

    1 reply 9 proslijeđenih tweetova 26 korisnika označava da im se sviđa
  20. 9. pro 2018.

    If you're looking for some light Sunday morning reading, I wrote a tutorial for fitting light curves using exoplanet (the code) and :

    15 proslijeđenih tweetova 69 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit

Nema rezultata.

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.