CS480/680 Lecture 18: Recurrent and recursive neural networks

Поделиться
HTML-код
  • Опубликовано: 18 ноя 2024

Комментарии • 18

  • @VahidOnTheMove
    @VahidOnTheMove 4 года назад +14

    It's unbelievably easy to understand the lecture. The best explanation I have seen.

  • @tahamagdy4932
    @tahamagdy4932 2 года назад +2

    Teachers should strive to be like you.
    Thank You

  • @datafiasco4126
    @datafiasco4126 9 месяцев назад

    Great job in explaining the concepts. Really liked the roll out diagrams.

  • @gregpaokfc
    @gregpaokfc Год назад

    Great lecture,really insightful and more relevant than ever. Thank you mr. Poupart.

  • @notanape5415
    @notanape5415 3 года назад +2

    Really amazing explanation for Attention! Thanks for making this lecture public.

  • @hadisjalesiyan1558
    @hadisjalesiyan1558 3 года назад +2

    Finally, I understood Attention. Thank you so much

  • @vitocorleone1991
    @vitocorleone1991 3 года назад +1

    Awesome, God bless you, professor.

  • @user-or7ji5hv8y
    @user-or7ji5hv8y 4 года назад

    Best explanation on attention so far for understanding the intuition.

  • @andrewmeowmeow
    @andrewmeowmeow 4 года назад +1

    Great lecture!

  • @rubenpartono
    @rubenpartono 3 года назад

    10:21 Being unfamiliar with how automatic differentiation works, this feels absolutely magical.

  • @micknamens8659
    @micknamens8659 2 года назад

    1:33:40 A mathematical graph has no fixed geometrical layout. Hence the distriction of functions u and v for "left" and "right" child seems odd.

    • @datafiasco4126
      @datafiasco4126 9 месяцев назад

      This is more akin to a tree in computing and hence legacy terminology is used as left and right child.

  • @user-or7ji5hv8y
    @user-or7ji5hv8y 4 года назад

    Does s3 depending on s2 and the convex combination of all of the h create unnecessary duplication, since s2 also depend on all the of h?

  • @user-or7ji5hv8y
    @user-or7ji5hv8y 4 года назад

    I don't see how under HMM, why the Y depend on X, given the direction of the arrow. Does the states depend on the past observations under HMM?

  • @puyncharasr6963
    @puyncharasr6963 4 года назад

    Thumb up

  • @samlaf92
    @samlaf92 5 лет назад

    50:00 Is this really an LSTM? Where's the "c" cell? Seems like a weird mix of LSTM and GRU...

    • @samlaf92
      @samlaf92 5 лет назад +1

      Nevermind. Should have waited until 59:00. I guess the "simple" version presented first around 50:00 would best be described as a peephole LSTM?