Ari Holtzman

@universeinanegg

PhD student studying how to make machines speak with social awareness. All opinions are my own.

Vrijeme pridruživanja: srpanj 2015.

Tweetovi

Blokirali ste korisnika/cu @universeinanegg

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

  1. proslijedio/la je Tweet
    31. sij

    "Scientific hypotheses and theories are not derived from observed facts, but invented in order to account for them." Hempel, 1966

    Poništi
  2. proslijedio/la je Tweet
    31. sij

    base from 🍊 (tangerine) eyes from 🌞 (sun) mouth from 🥳 (party-horn)

    Poništi
  3. proslijedio/la je Tweet
    18. sij

    Sometimes my colleagues who know I am skeptical about encoding-based notions of representation in cog sci ask me if I believe that deep neural networks have/use representations. This is the correct response (Bickhard and Terveen, 1995):

    Poništi
  4. proslijedio/la je Tweet
    18. sij

    fuck thyself

    Poništi
  5. proslijedio/la je Tweet

    One time when I was like 11 my dad took me to an Italian restaurant and the waiter asked what my name was and I said “Sam but you can call me captain ravioli” and my dad just looked at me and said “what the fuck was that? don’t do that” and I’ve been chasing that high ever since.

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

    Twitter has decided I want to see tweets about Transformers, lol

    Poništi
  7. proslijedio/la je Tweet
    11. sij

    Plot of a p-value, calculated for a simple t-test, for sample sizes of 10 to 2010, when the null hypothesis is true. Because p-values are uniformly distributed, the p-value just wanders randomly between 0 and 1. This is why repeatedly analyzing data as it comes in is not good!

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet

    The function x²ⁿ + y²ⁿ = 1 is the unit-circle for n=1, but approaches the unit-square as n→∞

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

    First, think about whether this sentence makes sense to or not? "The haystack was important because the cloth ripped" Most people say it seems grammatical but is incoherent. Perhaps it was generated by a (badly-tuned) neural language model! (1/N)

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

    If 1024 fair coins are each tossed 10 times, chances are good (> 63%) that at least one will come up heads 10 times in a row; and that coin will be proud to explain how its skill, faith, guts & determination made its achievement possible, and how that combo can work for you too.

    Prikaži ovu nit
    Poništi
  11. 2. sij
    Prikaži ovu nit
    Poništi
  12. 2. sij

    llpllllllllllllllllllllllllllllllpllllplllpll

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    30. pro 2019.

    I’d like to express my gratitude and admiration for who edited this piece I wrote. She pushed back in all the right ways and improved the essay, and also dealt with my stubbornness with grace. Thank you!

    Poništi
  14. 30. pro 2019.
    Poništi
  15. proslijedio/la je Tweet
    30. pro 2019.

    Duhem with a rousing speech for the study of scientific history by scientists.

    Poništi
  16. 28. pro 2019.

    My thoughts on the Deep Learning debate:

    Poništi
  17. proslijedio/la je Tweet
    27. pro 2019.
    Odgovor korisniku/ci

    Someone needs to propose a panel entitled “Titling Ourselves Into a Corner: Overpromising and Underdelivering at the Modern Academic Conference.”

    Poništi
  18. 23. pro 2019.

    Twitter made me realize I could gain access to people who study and care about the things I care about. But I care about a lot of things and there is literally no time to participate in all of them. The paralysis this creates is intense.

    Poništi
  19. proslijedio/la je Tweet
    20. pro 2019.

    counterfactuals, what would we do without them

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    20. pro 2019.

    How can narratology and NLP benefit from topological data analysis? First blog post!

    Prikaži ovu nit
    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:

    ·