Models as Code: Differentiable Programming with Zygote

แชร์
ฝัง
  • เผยแพร่เมื่อ 14 ม.ค. 2025

ความคิดเห็น • 6

  • @miketurner3461
    @miketurner3461 4 ปีที่แล้ว +7

    Arbitrary model differentiation is a major paradigm shift that I don't think people realize. ML Libraries/services are extremely declarative and/or black right now. Even something like tensorflow gradient tape relies on a lot of magic, and it gets stuck often when your use cases are less than standard. This makes it hard to:
    1) Deeply customize your model without working in odd or byzantine declarative paradigms (LOOKING AT YOU TENSORFLOW)
    2) Learn a model that's not currently in already well-known Machine Learning cannon
    This truly is a game changer and I think those of us who are learning how to do it now have a head start

  • @proweiqi
    @proweiqi 5 ปีที่แล้ว +14

    So few people here. Surprised.

  • @aadeshdeshmukh5275
    @aadeshdeshmukh5275 5 ปีที่แล้ว +7

    Julia is cool!!

  • @sucim
    @sucim 4 ปีที่แล้ว +1

    Awesome stuff!

  • @aoeu256
    @aoeu256 3 ปีที่แล้ว +2

    Is Julia the same thing as Common Lisp?

  • @DisruptarianRadio
    @DisruptarianRadio 5 ปีที่แล้ว

    "Ruby is rubbish! PHP is phpantastic!" author ~ "Nikita Popov"