Peilun Dai

@PeilunDai

Computer Science PhD Student at Boston University + +

Vrijeme pridruživanja: svibanj 2016.

Tweetovi

Blokirali ste korisnika/cu @PeilunDai

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

  1. proslijedio/la je Tweet

    I've just released a fairly lengthy paper on defining & measuring intelligence, as well as a new AI evaluation dataset, the "Abstraction and Reasoning Corpus". I've been working on this for the past 2 years, on & off. Paper: ARC:

    Prikaži ovu nit
    Poništi
  2. 3. kol 2019.

    How wonderful that AI could compose music for us, but if we are aware that there is no person with feelings behind the piece, will we treat the music the same as human-composed ones? via

    Poništi
  3. 3. kol 2019.

    The untold story of the ‘circle of trust’ behind the world’s first gene-edited babies

    Poništi
  4. 15. tra 2019.

    Interesting to see how political views vary across different languages. For me especially between English and Chinese. Learning a language bursts your national bubble via

    Poništi
  5. 9. sij 2019.

    I feel somehow, someday, some people will (or have?) create some version of a deep NN to discover the underlying structures in how different food is created

    Poništi
  6. 26. pro 2018.

    Very interesting idea, but how does causality structures at certain levels indicate consciousness of a system, maybe should go to the original papers. via

    Poništi
  7. 17. pro 2018.
    Poništi
  8. 18. stu 2018.

    “Today, there are more scientists, more funding for science, and more scientific papers published than ever before,” write  and . So why is the rate of significant discovery so low?

    Poništi
  9. 18. ruj 2018.
    Poništi
  10. proslijedio/la je Tweet
    27. kol 2018.
    Poništi
  11. proslijedio/la je Tweet
    6. srp 2018.

    Fascinating survey of the region. Science in East Asia — by the numbers

    Poništi
  12. 19. lip 2018.

    This has officially blown up my mind. Neural scene representation and rendering

    Poništi
  13. proslijedio/la je Tweet

    Why the network topology matters: It alone can give you much of the predictive power in biological networks. Our new paper, , soon in PNAS. Brought to you by and yours truly :)

    Poništi
  14. proslijedio/la je Tweet

    Perhaps the best/only way to explain neural networks to a five-year-old: (credit kouhoutek on )

    Poništi
  15. proslijedio/la je Tweet
    18. svi 2018.

    Justin Trudeau asking tough questions about how expansion microscopy works. (Photo credit: Holly Birns)

    Poništi
  16. 30. tra 2018.
    Poništi
  17. proslijedio/la je Tweet

    PyTorch 0.4.0 is out! lots of welcome additions: Variables/Tensor merge, more numpy-likeness (dtypes, *_like, pro indexing...), much easier to write CPU/GPU agnostic code, gradient checkpointing for memory-efficient backprop, reduce=False, distributions 👏

    Poništi
  18. proslijedio/la je Tweet
    23. tra 2018.

    Our work identifying genes regulating a simple behavior in is finally up at featuring collaboration between & students!

    Poništi
  19. proslijedio/la je Tweet
    30. sij 2018.

    Sydney Brenner: 'The young have a great advantage in that they are ignorant.  Because I think ignorance in science is very important. If you’re like me and you know too much you can’t try new things. I always work in fields of which I’m totally ignorant.'

    Poništi
  20. proslijedio/la je Tweet
    14. sij 2018.

    The next time someone tells you that a learning algorithm is "biologically implausible," remember that we probably haven't discovered half of the things neurons can do. Exhibit A: transsynaptic transmission of genetic material in virus-like capsids (!)

    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:

    ·