Размер видео: 1280 X 720853 X 480640 X 360
Показать панель управления
Автовоспроизведение
Автоповтор
It's unbelievably easy to understand the lecture. The best explanation I have seen.
Teachers should strive to be like you.Thank You
Great job in explaining the concepts. Really liked the roll out diagrams.
Great lecture,really insightful and more relevant than ever. Thank you mr. Poupart.
Really amazing explanation for Attention! Thanks for making this lecture public.
Finally, I understood Attention. Thank you so much
Best explanation on attention so far for understanding the intuition.
Awesome, God bless you, professor.
10:21 Being unfamiliar with how automatic differentiation works, this feels absolutely magical.
Great lecture!
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?
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.
This is more akin to a tree in computing and hence legacy terminology is used as left and right child.
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?
yes
50:00 Is this really an LSTM? Where's the "c" cell? Seems like a weird mix of LSTM and GRU...
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?
Thumb up
It's unbelievably easy to understand the lecture. The best explanation I have seen.
Teachers should strive to be like you.
Thank You
Great job in explaining the concepts. Really liked the roll out diagrams.
Great lecture,really insightful and more relevant than ever. Thank you mr. Poupart.
Really amazing explanation for Attention! Thanks for making this lecture public.
Finally, I understood Attention. Thank you so much
Best explanation on attention so far for understanding the intuition.
Awesome, God bless you, professor.
10:21 Being unfamiliar with how automatic differentiation works, this feels absolutely magical.
Great lecture!
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?
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.
This is more akin to a tree in computing and hence legacy terminology is used as left and right child.
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?
yes
50:00 Is this really an LSTM? Where's the "c" cell? Seems like a weird mix of LSTM and GRU...
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?
Thumb up