Scribd
Upload
39 views19 pages

Trí tuệ nhân tạo trong điều khiển: Convolutional Neural Networks Mạng nơron tích chập

The document discusses convolutional neural networks (CNNs) and their applications. It provides examples of how CNNs can be used for tasks like image classification, facial recognition, and self-driving cars. It also compares CNNs to regular neural networks, noting that CNNs are better suited for images due to local connectivity and shared weights. The document includes a toy example to illustrate how a basic CNN performs forward propagation on a sample input. It asks questions about where parameters come from and the benefits of local connectivity and shared weights in CNNs.

Uploaded by

Vỹ Trần
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
39 views19 pages

Trí tuệ nhân tạo trong điều khiển: Convolutional Neural Networks Mạng nơron tích chập

The document discusses convolutional neural networks (CNNs) and their applications. It provides examples of how CNNs can be used for tasks like image classification, facial recognition, and self-driving cars. It also compares CNNs to regular neural networks, noting that CNNs are better suited for images due to local connectivity and shared weights. The document includes a toy example to illustrate how a basic CNN performs forward propagation on a sample input. It asks questions about where parameters come from and the benefits of local connectivity and shared weights in CNNs.

Uploaded by

Vỹ Trần
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 19

Trí tuệ nhân tạo trong điều khiển

Convolutional Neural Networks


Mạng nơron tích chập
Review
Materials
What is CNNs?
✓Convolutional Neural Networks
❖ CNNs
❖ ConvNets
Applications
✓ Computer vision
❖ Face recognition
❖ Scene labeling
❖ Image classification
❖ Action recognition
❖ Human pose estimation
❖ Document analysis
✓ Natural language processing
❖ Speech recognition
❖ Text classification
Demo
✓ Demo:
❖ Image classification: http://cs231n.stanford.edu/
❖ Lane detection
❖ Off-Road Scenes Segmentation and Classification
❖ Self Driving Car
❖ Handwritten digits recognition
❖ Facial expression recognition
CNNs vs. Regular NNs
✓ Regular NNs: don’t scale well to full images
❖ CIFAR-10: image size 32x32x3
A single fully-connected neuron in a first hidden
layer has 32*32*3 = 3072 weights
❖ Image size: 200x200x3
200*200*3 = 120,000 weights
Over fitting
✓ CNNs: local connectivity
❖ Shared weights
What computers see pictures?
A toy example (forward)
X O

255 0 255 0 255 0

0 255 0 255 0 255

255 0 255 0 255 0


A toy example (forward)
Input I

I11 I12 I13

I21 I22 I23


P(I = X) = ?
I31 I32 I33 P(I = O) = ?

Convolution Layer: 2 kernels (4 weights


each) + 2 biases k111 k112 k211 k212
Fully Connected Layer: 16 weights
(regular NN) + 2 biases k121 k122 k221 k222

28 parameters Kernel 1 Kernel 2


Convolution layer
b1
dot product Activation
dot product b | map 1
1
I11 I12 I13
k111 k112 |
I21 I22 I23
k121 k122 |
I31 I32 I33 Kernel 1 b1
dot product |
dot product Activation
b1 = – 17.2 b1
map 2
b2 = – 25.1
k211 k212
f(x) = 1/(1 + e-x)

k111I11 + k112I12 k221 k222


+ k121I21 + k122I22 Kernel 2
A toy example (forward)
Case 1: X
1 0 w1 b3

0 1
| ? ~1

w8
0 1 w9 b
4

1 0 | ? ~0
w16
Activation map 1 & 2
w1, …, w8= [76.7 -76.2 -91.4 24.8 -92.7 24.3 -14.0 -71.3]
w8, …, w16= [-98.9 69.6 77.5 -96.6 18.9 -53.8 -96.0 99.4]
b3, b4= [-47.9 -60.0]
A toy example (forward)
Case 2: O
0 1 w1 b3

1 0
| ? ~0

w8
1 0 w9 b
4

0 1 | ? ~1
w16
Activation map 1 & 2
w1, …, w8= [76.7 -76.2 -91.4 24.8 -92.7 24.3 -14.0 -71.3]
w8, …, w16= [-98.9 69.6 77.5 -96.6 18.9 -53.8 -96.0 99.4]
b3, …, b4= [-47.9 -60.0]
Questions
Q: Where do all parameters come from?
A: Backpropagation

Q: Why local connectivity?

Q: Why shared weights?


General cases
b

|
4 weights
1 bias 27 weights
1 bias
R, G, B layers

|
General cases
Convolution layer 1 b
|

|
b

K activation maps

K kernels
General cases
Pooling/Subsample layer

10x10 matrices 5x5 matrices


General cases
Convolutional layer 2 b

|

4 weights 27 weights
1 bias 1 bias

|

36 weights 1 bias
General cases
Fully Connected Layer

You might also like