ODE | Neural Ordinary Differential Equations - Best Paper Awards NeurIPS

แชร์
ฝัง
  • เผยแพร่เมื่อ 24 ธ.ค. 2024

ความคิดเห็น • 21

  • @nathancooper1001
    @nathancooper1001 5 ปีที่แล้ว +21

    Exciting work! I look forward to to being able to eventually understand it haha

  • @TheSam1902
    @TheSam1902 5 ปีที่แล้ว +5

    This video is amazing. Researching this very paper since last week and seeing the actual presentation is lifesaving

  • @declan6052
    @declan6052 6 หลายเดือนก่อน +1

    Wow, at 9:59 we see the very beginning of diffusion models! Very cool to see something so impactful in its infancy

  • @rstar0000
    @rstar0000 5 ปีที่แล้ว +3

    Amazing work!

    • @DrOsbert
      @DrOsbert  5 ปีที่แล้ว

      Please do support our channel by subscribing and sharing the video to others. Love & Peace!

  • @dustinkendall3365
    @dustinkendall3365 5 ปีที่แล้ว

    So do these odes model a function as simply a function of time, because I want to make it as a function of time with position and velocity as initial condition parameters. How do I do this?

    • @rickymort135
      @rickymort135 ปีที่แล้ว

      well it's ODEs of the form x' = f(x, t) so f is modelling the velocity - the only inputs you can put in are positions and time. To input velocity you'd need f to give you: f(initial_position) = initial_velocity. This is a little tricky. You could include include training examples [initial_position, initial_velocity] and train f on this with a big penalty for deviation

  • @bananarobotoverlord
    @bananarobotoverlord 5 ปีที่แล้ว +1

    So 1/2 the parameters, but 2-4x the FLOPs?

    • @DrOsbert
      @DrOsbert  5 ปีที่แล้ว

      You can say so but It depends on the actual use case

  • @OneShot_cest_mieux
    @OneShot_cest_mieux 4 ปีที่แล้ว

    What is theta please ? I don't understood.

    • @youcancode6988
      @youcancode6988 4 ปีที่แล้ว

      Theta is the parameters

    • @OneShot_cest_mieux
      @OneShot_cest_mieux 4 ปีที่แล้ว

      @@youcancode6988 What parameter for example ? And theta seems to be a function of time

    • @OneShot_cest_mieux
      @OneShot_cest_mieux 4 ปีที่แล้ว

      @@youcancode6988
      I hope you don't comment your code by writing "var1 is the first parameter, var2 is the second parameter, [...]"

    • @youcancode6988
      @youcancode6988 4 ปีที่แล้ว +3

      @@OneShot_cest_mieux Theta is the weighted values given to each input on each node in each layer of the neural network

    • @OneShot_cest_mieux
      @OneShot_cest_mieux 4 ปีที่แล้ว

      @@youcancode6988 ok thank you

  • @ranam
    @ranam 5 ปีที่แล้ว +1

    2:26

  • @iworeushankaonce
    @iworeushankaonce 4 ปีที่แล้ว +4

    Amazing talk, and a huge dislike for the amount of commercials you put in this video. shame