ICLR Debate with Leslie Kaelbling (ICLR 2019)

แชร์
ฝัง
  • เผยแพร่เมื่อ 2 ก.พ. 2025

ความคิดเห็น • 8

  • @Kram1032
    @Kram1032 5 ปีที่แล้ว +1

    That panel was amazing. I hope there will be more of these!
    Personally, I like all of the research directions taken here.

  • @KaplaBen
    @KaplaBen 5 ปีที่แล้ว +9

    21:06 Jeff Clune at 100% cpu

    • @ikeyang
      @ikeyang 4 ปีที่แล้ว

      This comment made my day

  • @snippletrap
    @snippletrap 4 ปีที่แล้ว +1

    Neural networks didn't start working well until priors were built into the architecture.

  • @snippletrap
    @snippletrap 4 ปีที่แล้ว

    At 30:30 -- models can't learn about causality. Hume and Kant already went over this. If you want causality, you have to supply it yourself.

  • @pervezbhan1708
    @pervezbhan1708 5 ปีที่แล้ว

    Joshua Tenenbaum work free for google, same as we people mostly do work for google without payment

    • @robosergTV
      @robosergTV 5 ปีที่แล้ว

      you are getting back form google the services you are using. So you dont work for free.

  • @snippletrap
    @snippletrap 4 ปีที่แล้ว

    Suchi Saria seems a little out of her depth here.