Eric Bigelow

@bigel_o

into language, minds, and computation

Vrijeme pridruživanja: kolovoz 2009.
5 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @bigel_o

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

  1. proslijedio/la je Tweet
    11. svi 2019.

    How words change meaning over time: “Baseline” (in NLP) 1998: random choice 2005: majority class 2012: bag of words 2019: LSTM with attention & pre-trained embeddings

    10 replies 212 proslijeđenih tweetova 1.232 korisnika označavaju da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    23. ožu 2019.

    If you're lucky enough to write a thread that blows up and is read by lots of smart people, turns out you get sent some really amazing stuff! 😊 This is another thread to list 31 (!!!) of the interesting related things people mentioned in the replies:

    My best kept secret* is that string & wiring diagrams--plucked straight out of applied category theory--are *fabulous* for software and system design. And you don't have to learn a damn thing to start using them. 🙌 *will talk to anyone who'll listen
    Prikaži ovu nit
    52 proslijeđena tweeta 207 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    24. kol 2018.

    Facts that may or may not be obvious: - Jupyter is a nod to 3 languages: Julia, Python, and R - the "gg" in ggplot stands for "Grammar of Graphics" - Pandas comes from "panel data" - naming things is hard, but once the names are out there people rarely think about them

    59 replies 1.458 proslijeđenih tweetova 5.306 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    5. lip 2018.

    Just finished reading through DeepMind's / et al.'s new review/position paper on graph neural nets: Timely and highly relevant contribution to the field IMO, couldn't agree more with their motivation for this class of models

    77 proslijeđenih tweetova 279 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. 11. lis 2017.

    Nice high-level talk on causal inference by Judea Pearl:

    3 korisnika označavaju da im se sviđa
    Poništi
  6. 27. kol 2017.

    Paper idea: "obfuscating political agendas by gradient dissent"

    1 reply 2 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    24. kol 2017.

    heck

    159 proslijeđenih tweetova 534 korisnika označavaju da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    8. lip 2017.

    So I took some time and wrote this medium post about this language generation paper.

    Odgovor korisniku/ci @yoavgo
    Maybe it's worth considering writing a blog post with some analysis in case you feel that strongly about it?
    35 replies 293 proslijeđena tweeta 568 korisnika označava da im se sviđa
    Poništi
  9. 29. tra 2017.

    "Mathematics studies the way our brains work."

    Is our mathematics somehow constrained by the laws of physics? If so, could there possibly be alternate universes w…
    2 proslijeđena tweeta
    Poništi
  10. proslijedio/la je Tweet
    1. ožu 2017.

    30 years of user interface design... progress?

    1.653 proslijeđena tweeta 2.370 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    3. velj 2017.
    Odgovor korisniku/ci

    FMRI is like figuring out source code from seeing how often different functions are called.

    6 proslijeđenih tweetova 9 korisnika označava da im se sviđa
    Poništi
  12. 29. sij 2017.

    Should social science be more solution-oriented?

    1 korisnik označava da mu se sviđa
    Poništi
  13. 19. sij 2017.

    I sent @amazonecho feedback saying I wanted to use "computer" as my echo's wake word... without saying anything, they enabled this for me 👏

    Poništi
  14. proslijedio/la je Tweet
    3. sij 2017.

    No offense, but I gotta poke fun here. The fact that in 2 yrs, AI has been reduced to classification challenges is sadly hilarious :-/

    Fun thought experiment: what are the best ways to measure AI beyond scores on classification challenges?
    11 replies 22 proslijeđena tweeta 75 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    31. pro 2016.

    Life in life -the hashlife algorithm blew my mind when i first understood it. still amazes me

    5 replies 53 proslijeđena tweeta 104 korisnika označavaju da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    27. pro 2016.

    Emerging Frontiers of Neuroengineering: A NetSci of Brain Connectivity, accepted to ANNU REV BIOMED ENG:

    28 proslijeđenih tweetova 36 korisnika označava da im se sviđa
    Poništi
  17. 9. pro 2016.

    Minsky & Chomsky (12/9/16) - "Brains, Minds and Machines"

    Poništi
  18. proslijedio/la je Tweet
    5. pro 2016.

    Delightful guide to writing clear scientific papers by

    1 reply 250 proslijeđenih tweetova 381 korisnik označava da mu se sviđa
    Poništi
  19. 3. pro 2016.

    what if elmo, cookie monster, and oscar represent the same person at three different times in their life?

    1 korisnik označava da mu se sviđa
    Poništi
  20. proslijedio/la je Tweet
    28. stu 2016.

    "Learning to Compose Words into Sentences with Reinforcement Learning," Yogatama et al. at DeepMind:

    16 proslijeđenih tweetova 21 korisnik označava da mu se sviđa
    Poništi

@bigel_o 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:

    ·