Rahul Deora

@rahuld3eora

Against the learning metaphor

Vrijeme pridruživanja: rujan 2011.
2 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @rahuld3eora

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @rahuld3eora

  1. proslijedio/la je Tweet
    3. velj

    In January, , , and I ran a short class at on topics we think are missing in most CS programs — tools we use every day that everyone should know, like bash, git, vim, and tmux. And now the lecture notes and videos are online!

    11 replies 307 proslijeđenih tweetova 926 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    1. velj

    how to mess with your coworkers

    111 replies 1.043 proslijeđena tweeta 4.560 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    31. sij

    If you're running xgboost, lgbm, or other forest based models in production you need to check out our new forest inference library. 40x faster predictions, cheaper than cpu and way less rack space.

    40x faster predictions for even the deepest random forests with FIL’s new sparse forest support -
    69 proslijeđenih tweetova 308 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    30. sij

    Legitimately one of the best insights I've internalized after years of doing research is the old classic - "ideas are cheap, execution is everything" [not quite everything, we still need cool ideas, but y'know]

    Every. Single. Time.
    62 proslijeđena tweeta 373 korisnika označavaju da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    29. sij

    This Monday, in class, explained how the retina performs a 100× compression to go from 100M photoreceptors to 1M axons in the optic nerve. As a consequence, the central object in this video appears to become brighter / darker although its brightness is constant. – mjesto: NYU Center for Data Science

    0:16
    Combined circles
    69 proslijeđenih tweetova 317 korisnika označava da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    28. sij

    I was listening to an excellent podcast by and was reminded of this passage from Newell and Simon’s 1975 Turing Award Lecture, where I imagined replacing “computer science” with “statistics ” and “machine” with “model”

    4 proslijeđena tweeta 10 korisnika označava da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    28. sij

    "There's no relevant data on what you want to know. We could collect some irrelevant data and run a deep neural network on it."

    23 proslijeđena tweeta 68 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    28. sij

    "Your assumptions are your windows on the world. Scrub them off every once in a while, or the light won't come in." -- Isaac Asimov

    15 replies 1.545 proslijeđenih tweetova 4.312 korisnika označava da im se sviđa
    Poništi
  9. 22. sij

    Tabular Data differentiable NODE

    I've blogged about my go-to tool for prediction on tabular data, CatBoost, and its differentiable (neural network based) counterpart, NODE. Future blog posts on other tools to follow!
    1 korisnik označava da mu se sviđa
    Poništi
  10. proslijedio/la je Tweet
    20. sij

    I've blogged about my go-to tool for prediction on tabular data, CatBoost, and its differentiable (neural network based) counterpart, NODE. Future blog posts on other tools to follow!

    6 proslijeđenih tweetova 33 korisnika označavaju da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    17. sij

    Really interesting visualisation of how various DR techniques (including ) embed a complex dataset. 1,000,000 points visualised with the help of .

    6 replies 78 proslijeđenih tweetova 248 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    15. sij

    The central limit theorem began in 1733 when de Moivre approximated binomial probabilities using the integral of exp(-x^2).

    1 reply 43 proslijeđena tweeta 118 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    15. sij

    The *easiest* way to learn Deep Learning is to build it from scratch! IMO, the same is true when learning a Deep Learning framework. In I show how to build a -like framework Here's the step-by-step code!!

    8 replies 207 proslijeđenih tweetova 981 korisnik označava da mu se sviđa
    Poništi
  14. proslijedio/la je Tweet
    14. sij

    Natural Image Matting via Guided Contextual Attention pdf: abs: github:

    6 proslijeđenih tweetova 11 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    8. sij

    A good listing of tricks for ML research. Probably combining any two of these could get you a paper at a conference. Please don't do that blindly. Slide by .

    1 reply 65 proslijeđenih tweetova 351 korisnik označava da mu se sviđa
    Poništi
  16. proslijedio/la je Tweet
    8. sij

    Interesting post on one of the times GANs were invented in the 90's. (See the final paragraph for a link to the source code, and even coverage in MSNBC!)

    31 proslijeđeni tweet 169 korisnika označava da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    2. stu 2019.

    Postbox is such a brilliant idea! Instead of continuously being bombarded by notifications, the app collects them and delivers them all together 3 times a day. Why isn't this an Android default?

    18 proslijeđenih tweetova 100 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    3. sij

    I'm biased here, but this is one of the strongest visual illusions I have ever seen. None of the colored lines are moving.

    75 replies 1.722 proslijeđena tweeta 4.664 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    3. sij

    "When one teaches, two learn." -- Robert Heinlein

    19 replies 1.638 proslijeđenih tweetova 6.084 korisnika označavaju da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    27. pro 2019.

    In 1944, the CIA distributed a Simple Sabotage Field Manual with instructions for discretely making organizations less effective. Useful lens for noticing where organizations can become unintentionally self-sabotaging. HT

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
    5 replies 74 proslijeđena tweeta 226 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi

@rahuld3eora 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:

    ·