Tweetovi

Blokirali ste korisnika/cu @pmbaumgartner

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

  1. Prikvačeni tweet
    15. stu 2019.
    Poništi
  2. I also created an app to serve as an example of some of these concepts. It uses data from a research paper that evaluated THC and CBD lab measurements of cannabis products in Washington State.

    Prikaži ovu nit
    Poništi
  3. The new stuff includes two themes for Altair that match the default theme of streamlit apps.

    Prikaži ovu nit
    Poništi
  4. I combined the content from my previous "Intermediate Streamlit" article plus some new notes I'd taken into my own "Streamlitopedia". If you're using , maybe there's something helpful in here for you.

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    31. sij

    The way we talk about data science and focus so much on methods, we actually incentivize working with *bad* data, rather than spending the time to collect good data and then use easy methods with it

    Prikaži ovu nit
    Poništi
  6. Snarky, but some good points. Reminds me of Gelman's time-reversal heuristic.

    Poništi
  7. proslijedio/la je Tweet
    23. sij

    - GitHub Repo Spotlight №6 NLP library that incorporates many Deep Learning-based models into one easy to use package called gobbli:

    Poništi
  8. proslijedio/la je Tweet
    23. sij

    I have a new paper with , forthcoming in AEA P&P "Algorithmic Social Engineering" We apply classic strategic communication models to "fair machine learning". In a nutshell: nudging people to change behavior by tweaking an algorithm is hard! 1/

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    30. sij

    The story of this paper is Paul & I wanted to highlight: (1) how opaque inference is to most scientists (is essentially superstition) (2) how bad inferential methods can become normative So the paper combines both. I wrote the title. Paul did the rest.

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    22. sij

    "Science is messy, and the results of research rarely conform fully to plan or expectation. ‘Clean’ narratives are an artefact of inappropriate pressures and the culture they have generated." Fabulous editorial from . More editors sign on?

    Poništi
  11. 28. sij

    Same thing with 100 total points and color.

    Prikaži ovu nit
    Poništi
  12. 28. sij

    Anyone know of any work visualizing confusion matrices by density or count? I feel this is a nice way to get a holistic view of classifier performance and understanding how relatively often each outcome happens. (300 points plotted below)

    Prikaži ovu nit
    Poništi
  13. 26. sij

    My favorite genre of Hacker News post is <random link to page of SQLite docs>.

    Poništi
  14. proslijedio/la je Tweet
    24. sij

    The coda to 's interview with is shocking. As described on : He screamed, swore at her, and said she couldn't find Ukraine on a map. He ordered staffers to bring a blank map. She pointed to Ukraine and thanked him for his time.

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    25. sij

    I see no potential downside

    Poništi
  16. 19. sij
    Poništi
  17. proslijedio/la je Tweet
    18. sij

    A thread of classifiers learning a decision rule. Dashed line is optimal boundary. Animations with by and . Logistic regression {stats::glm} with each class having normally distributed features. (1/n)

    Prikaži ovu nit
    Poništi
  18. 17. sij

    Anyone using ALBERT from transformers for non-benchmark tasks? For some reason it won't work for me on a classification task. Training loss an order of magnitude (or more) higher on ALBERT compared to BERT and RoBERTa (base and large).

    Poništi
  19. 16. sij

    I have used the python version of this for this exact use case: sending variable names over email. Super helpful. ", ".join(df.columns)

    Poništi
  20. 14. sij

    Triangle folks: come hang out with Jason and I and learn about the NLP library we're developing tonight!

    Poništi
  21. 13. sij

    "Sentiment Analysis" is a synecdoche for qualitative coding.

    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:

    ·