Share
Embed
Slide 1
Slide 1 text
The backbone of modern computer vision
Intro to ConvNets
Slide 2
Slide 2 text
2
Slide 3
Slide 3 text
3
=
Slide 4
Slide 4 text
4
Slide 5
Slide 5 text
Convolutional Network
Slide 6
Slide 6 text
6
⊙ =
Σ
input
output
kernel
Slide 7
Slide 7 text
7
input
output
⊙ =
kernel
Σ
Slide 8
Slide 8 text
8
input
output
=
kernel
Σ
⊙
Slide 9
Slide 9 text
9
input
output
⊙ =
kernel
Σ
Slide 10
Slide 10 text
10
kernel
input output
Slide 11
Slide 11 text
11
Slide 12
Slide 12 text
12
Optimization
Label: Bird
ConvNet
Loss
Function
Prediction: Cat
Slide 13
Slide 13 text
13
Optimization
ConvNet Prediction: Bird
Loss
Function
Label: Bird
Slide 14
Slide 14 text
14
Non-linear function
from: wikipedia.org
Sigmoid Function
Slide 15
Slide 15 text
15
Pooling operation
from: computersciencewiki.org
Slide 16
Slide 16 text
16
Slide 17
Slide 17 text
17
Conv layer
Non-linear function
Convolution & Non-linear function & Pooling
Pooling
Conv layer
Non-linear function
Pooling
Conv layer
Non-linear function
Slide 18
Slide 18 text
18
AlexNet (2012)
Slide 19
Slide 19 text
Thanks!