Torsten Scholak

@tscholak

applied research scientist , formerly physicist , into natural language processing, Bayesian stats, and functional programming in

Montréal
Vrijeme pridruživanja: veljača 2010.

Medijski sadržaj

  1. 20. sij
    Odgovor korisniku/ci
  2. 19. sij

    after a few days of searching for the right abstractions, I got data parallelism working in

    Prikaži ovu nit
  3. 19. sij

    It is absolutely astonishing how quickly was able to put this together: has fully migrated to libtorch 1.4.0! Thank you Junji!

  4. 16. sij
  5. 14. sij
    Odgovor korisniku/ci

    thank you, I'll have a look. I was thinking about queries in terms of FOL terms as shown in the picture

  6. 13. sij
  7. 26. pro 2019.

    thanks , your generic-lens paper gave me the insight I needed to implement the HasToDevice class and instances for ! 🥳

  8. 23. pro 2019.
    Odgovor korisniku/ci

    Here’s a fully functional convolutional neural network in Haskell. This API wraps libtorch, and the compiler checks your shapes, data types and physical devices, and it tells you how functions change them (see the hover box for unsqueeze).

  9. 24. lis 2019.
    Odgovor korisniku/ci
  10. 24. lis 2019.

    need a better name for this type class vvv

  11. 15. lis 2019.
    Odgovor korisnicima
  12. 11. lis 2019.
    Odgovor korisniku/ci
  13. 6. lis 2019.
    Odgovor korisniku/ci

    Can I interest you in some Haskell?

  14. 1. lis 2019.
    Odgovor korisniku/ci

    because they are Klingon? at around 1 min in

  15. 30. ruj 2019.

    it's coming together

  16. 28. ruj 2019.

    one down, many more to go

  17. 27. ruj 2019.
    Odgovor korisniku/ci
  18. 11. ruj 2019.
    Prikaži ovu nit
  19. 7. kol 2019.

    Had a blast today at with @cntewfik. It was really engaging and renewed our appreciation of Canadian paintings. Canadian artists established their own style using the whole world as their landscape. Just like Canadian culture.

  20. 20. lip 2019.
    Odgovor korisnicima i sljedećem broju korisnika:

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:

    ·