Terence Parr

@the_antlr_guy

Posts by Terence Parr, The ANTLR guy, most recently about machine learning but also stuff about ANTLR, general computer languages.

San Francisco
Vrijeme pridruživanja: prosinac 2010.

Tweetovi

Blokirali ste korisnika/cu @the_antlr_guy

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

  1. Prikvačeni tweet
    20. lip 2018.

    Launched a new website, , dedicated to giving deep but intuitive explanations of machine learning and related topics.

    Poništi
  2. 27. sij

    Now this is the kind of academic research I can get behind! "Systematically Improving Espresso: Insights from Mathematical Modeling and Experiment: Matter"

    Poništi
  3. 23. sij

    . makes it look easy with "The Unreasonable Effectiveness of Recurrent Neural Networks"

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

    Working on a language parsing project using ANTLR this weekend, and I’m constantly amazed at how often it just works without any fuss. Kudos to , , Mike Lischke, et al for the awesome work!

    Poništi
  5. 23. sij

    I'd love to see what a recurrent neural net would do, compared to the feature engineering + kNN approach and I took!

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

    There's a *lot* of people that are under the impression that publishers pay for stuff that's actually done by volunteers or open source software. As a result, many people over-estimate the amount of costs that are reasonable to expect.

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    20. sij

    Interesting paper showing how dozens of studies have accidentally leaked large amounts of data from train->test dataset, by duplicating data items prior to doing a random split.

    Poništi
  8. 21. sij

    Thanks! I finally found the right "voice" in that book :)

    Poništi
  9. 20. sij

    New PHP target (by ) for ANTLR parser generator in new release 4.8; StringTemplate 4.3 also released. Get 'em while they're hot. and

    Poništi
  10. proslijedio/la je Tweet
    13. sij

    Happy New Year, Twitter! MSDS is holding two more info sessions this spring for information on how to apply for Summer 2020: Jan 15 (Wednesday!) and Feb 7. RSVP here:

    Poništi
  11. proslijedio/la je Tweet
    14. sij

    At medical imaging we often need to make a little data go a long way. One under-appreciated approach for this is self-supervised learning. It's almost magical! I've written a little overview to help you get started. Let me know if you try it :)

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    11. sij

    Oh and BTW, if you want to be one of the first to see this material, then you'll want to join our Deep Learning course in SF, running for 8 weeks from March 17, 2020. Apply here:

    Poništi
  13. proslijedio/la je Tweet
    11. sij

    In our forthcoming book & course, you'll learn how to build a real deep learning web app from scratch, including downloading images using Bing's API. You'll also learn what can go wrong! (h/t )

    Poništi
  14. 23. pro 2019.

    My two favorite things, ML and compilers!! Great to meet you and Uma.

    Poništi
  15. proslijedio/la je Tweet

    Join us as a postdoc next year for an opportunity to work with our industry partners or our research initiatives in AI & medicine, environment & human rights, applied data ethics and more. Deadline is Jan 7! Check out our current postdocs and apply:

    Poništi
  16. proslijedio/la je Tweet
    11. pro 2019.

    The v3 of the course (part 1) is now fully ported to fastai v2 (and by ported, it's not just the code runs but the results match or exceed the ones from the version on fastai v1). All notebooks are here:

    Prikaži ovu nit
    Poništi
  17. 4. pro 2019.

    dtreeviz 0.8 (decision tree visualizer) released with fixes and new features by . pip install -U dtreeviz See

    Poništi
  18. 4. pro 2019.
    Poništi
  19. proslijedio/la je Tweet
    3. pro 2019.

    I will be teaching a 6-week Intro to Data Ethics Course: 6-8pm on Monday evenings, Jan 27-March 9 Downtown SF (101 Howard St) No prereqs, scholarships available Please join me for it!

    Prikaži ovu nit
    Poništi
  20. 29. stu 2019.
    Poništi
  21. proslijedio/la je Tweet
    28. stu 2019.

    Starting to build the parser for a gherkin-like language on an internal project. Using , and can heartily recommend the book by . Easy to read, and the examples all work when I switch them over to C# targets rather than Java!

    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:

    ·