Speech Recognition | ⟶ | Get your facts first, then you can distort them as you please. | |
Music generation | ∅ | ⟶ | |
Sentiment classification | Great movie ? Are you kidding me ! Not worth the money. | ⟶ | |
DNA sequence analysis | ACGGGGCCTACTGTCAACTG | ⟶ | AC GGGGCCTACTG TCAACTG |
Machine translation | 网红脸 | ⟶ | Internet celebrity face |
Video activity recognition | ⟶ | Running | |
Name entity recognition | Use Netlify and Hugo. | ⟶ | Use Netlify and Hugo. |
x: Use(x<1>) Netlify(x<2>) and(x<3>) Hugo(x<4>) .(x<5>)
y: 0 (y<1>) 1(y<2>) 0(y<3>) 1(y<4>) 0(y<5>)
x(i)<t>, T(i)x (ith sample)
y(i)<t>, T(i)y (ith sample)
[a[1]aaron[2]⋮and[360]⋮Hugo[4075]⋮Netlify[5210]⋮use[8320]⋮Zulu[10000]]⟹use=[00⋮0⋮0⋮0⋮1⋮0],Netlify=[00⋮0⋮0⋮1⋮0⋮0],and=[00⋮1⋮0⋮0⋮0⋮0],Hugo=[00⋮0⋮1⋮0⋮0⋮0]
x: Use(x<1>) Netlify(x<2>) and(x<3>) Hugo(x<4>) .(x<5>)
y: 0 (y<1>) 1(y<2>) 0(y<3>) 1(y<4>) 0(y<5>)
x(i)<t>, T(i)x (ith sample)
y(i)<t>, T(i)y (ith sample)
a<0>=o; a<1>=g(Waaa<0>+Waxx<1>+ba)
ˆy<1>=g′(Wyaa<1>+by)
a<t>=g(Waaa<t−1>+Waxx<t>+ba)
ˆy<t>=g′(Wyaa<t>+by)
L<t>(ˆy<t>)=−y<t>log(ˆy<t>)−(1−y<t>)log(1−ˆy<t>)
L(ˆy,y)=ΣTyt=1L<t>(ˆy<t>,y<t>)
eman−ewoman≈eking−e?
→argmaxw{sim(ew,eking−eman+ewoman)}
sim(ew,eking−eman+ewoman) = ?
Cosine similarity: sim(a,b)=aTb||a||2||b||2
sim(ew,eking−eman+ewoman) = ?
Cosine similarity: sim(a,b)=aTb||a||2||b||2
Space, Right Arrow or swipe left to move to next slide, click help below for more details