SlideShare ist ein Scribd-Unternehmen logo
1 von 64
CNN - Convolutional Neural Network
Yung-Kuei Chen Craig
Summary
•Why do we need Convolutional Neural Network?
Problems
Solutions
•LeNet Overview
Origin
Result
•LeNet Techniques
Structure
Why do we need Convolutional Neural Network?
Problems
Source: MNIST database
Solution
Source: MNIST database
𝑓( )= 5
Problems
Source : Volvo autopilot
Solution
Source : Volvo autopilot
𝑓( )
LeNet
Image recognition
Introduce
Yann LeCun
•Director of AI Research, Facebook
main research interest is machine learning, particularly
how it applies to perception, and more particularly to
visual perception.
• LeNet Paper:
Gradient-Based Learning Applied to Document Recognition.
Source : Yann LeCun, http://yann.lecun.com/
Introduce
Introduce
K nearest neighbors Convolutional NN
•Revolutionary
Even without traditional machine learning
concept, the result*(Error Rate:0.95%) is
the best among all machine learning
method.
Introduce
*LeNet-5, source : Yann LeCun, http://yann.lecun.com/exdb/mnist/
0 2 4 6 8 10 12 14
linear classifier (1-layer NN)
K-nearest-neighbors, Euclidean (L2)
2-layer NN, 300 hidden units, MSE
SVM, Gaussian Kernel
Convolutional net LeNet-5
TEST ERROR RATE (%) (The lower the better)
Introduce
Overview
Source : [LeCun et al., 1998]: Gradient-Based Learning Applied to Document Recognition Page. 7
Input
Source : [LeCun et al., 1998]: Gradient-Based Learning Applied to Document Recognition Page. 7
Input Layer
Data : MNIST handwritten digits
training set : 60,000 examples
test set : 10,000 examples
Source : http://yann.lecun.com/exdb/mnist/
Input Layer
Source : http://yann.lecun.com/exdb/mnist/
Data : MNIST handwritten digits
training set : 60,000 examples
test set : 10,000 examples
Size : 28x28
Color : Black & White
Range : 0~255
Input Layer – Constant(Zero) Padding
Source : http://xrds.acm.org/blog/2016/06/convolutional-neural-networks-cnns-illustrated-explanation/
1.To make sure the data input
fit our structure.
2.Let the edge elements have
more chance to be filtered.
Without Padding With Padding
Convolutional Layer
Source : [LeCun et al., 1998]: Gradient-Based Learning Applied to Document Recognition Page. 7
Convolutional Layer – Function
Extract features from the input image
Source : An Intuitive Explanation of Convolutional Neural Networks
https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/
Convolution
Convolution is a mathematical operation on two functions to
produce a third function, that is typically viewed as a
modified version of one of the original functions.
Convolutional Layer Overview
Convolutional Layer = Multiply function + Sum Function
Layer input
Kernel
Layer
output
Source : https://mlnotebook.github.io/post/CNN1/
Multiply Sum
1 0 1
0 1 0
1 0 1
Convolutional Layer – Kernel
1.Any size
2.Any Shape
3.Any Value
4.Any number
Source : https://cambridgespark.com/content/tutorials/convolutional-neural-networks-with-keras/index.html
Convolutional Layer – Computation
Multiply
Sum
Convolutional Layer – Computation
Layer input
Kernel
Layer
output
Source : https://mlnotebook.github.io/post/CNN1/
Convolutional Layer – Computation
3x3 Kernel
Padding = 0
Stride = 1
Shrunk Output
Source: https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/convolutional_neural_networks.html
Convolutional Layer – Stride
Stride = 1 Stride = 2
Source: Theano website
Convolutional Layer – Computation
3x3 Kernel
Padding = 1
Stride = 1
Same Size Output
Source: Theano website
Convolutional Layer Overview
Layer input
Kernel
Layer
output
Source : https://mlnotebook.github.io/post/CNN1/
-1 0 1
-2 0 2
-1 0 1
1 2 1
0 0 0
-1 -2 -1
X filter
Y filter
Result
Convolutional Layer – Result
Source : Deep Learning in a Nutshell: Core Concepts, Nvidia
https://devblogs.nvidia.com/parallelforall/deep-learning-nutshell-core-concepts/
Low-level feature Mid-level feature High-level feature
Pooling Layer(Subsampling)
Source : [LeCun et al., 1998]: Gradient-Based Learning Applied to Document Recognition Page. 7
Pooling Layer – Function
Reduces the dimensionality of each feature map
but retains the most important information
Source : An Intuitive Explanation of Convolutional Neural Networks
https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/
Pooling Layer Overview.
Source : Using Convolutional Neural Networks for Image Recognition
https://www.embedded-vision.com/platinum-members/cadence/embedded-vision-
training/documents/pages/neuralnetworksimagerecognition#3
Pooling Layer – Max Pooling
Source : Stanford cs231
http://cs231n.github.io/convolutional-networks/
Source : Tensorflow Day9 卷積神經網路 (CNN) 分析 (2) - Filter, ReLU, MaxPolling
https://ithelp.ithome.com.tw/articles/10187424
Kernel : 2x2
Stride : 2
Padding : 0
Pooling Layer – Max Pooling
Pooling Layer – Examples
Fully Connection
Source : [LeCun et al., 1998]: Gradient-Based Learning Applied to Document Recognition Page. 7
Fully Connection – Function
1.Flatten the high dimensional input
Fully Connection – Function
2.Learning non-linear combinations of
these features.
Fully Connection Overview
The fully connected means that
every two neurons in each layer
are connected.
How Neural Network works?
1
-1
1
1
-1
-2
1
4
-2
0.98
0.12
𝑦1
𝑦2
Sigmoid
0
Source : professor Hung-yi Lee Deep Learning slides page.12
Input Output
(1 x 1) + (-1 x -2) + 1
(1 x -1) + (-1 x 1) + 0
Sigmoid
Activation Functions
Sigmoid
Activation Functions
ReLU Tanh
Output
Source : [LeCun et al., 1998]: Gradient-Based Learning Applied to Document Recognition Page. 7
Output – Loss Function (Least Squared error )
Output 𝑌 = 𝑆𝑈𝑀((𝑋 𝑇
− 𝑊)2
)
Loss Function (Cost Function):
To evaluate the difference between predicted
value and the answer.
[ ]
Output – One hot encoding
9
Make sure the differences between any
pair of numbers are the same.
Output – One hot encoding
9-8 = 1 Closer!!!
9-5 = 3 Farther!!
Make sure the differences between any
pair of numbers are the same.
Output – One hot encoding
0:
1:
2:
3:
4:
5:
6:
7:
8:
9:
0:
1:
2:
3:
4:
5:
6:
7:
8:
9:
0:
1:
2:
3:
4:
5:
6:
7:
8:
9:
0:
1:
2:
3:
4:
5:
6:
7:
8:
9:
Output – One hot encoding
12 + 12 = 2 12 + 12 = 2
Distance between two dots
Output
How can we
estimate the result?
0:
1:
2:
3:
4:
5:
6:
7:
8:
9:
Output
0:
1:
2:
3:
4:
5:
6:
7:
8:
9:
0:
1:
2:
3:
4:
5:
6:
7:
8:
9:
9
Ps: The digit in Matrix is only for
expression, not the real calculation
Overview
Source : [LeCun et al., 1998]: Gradient-Based Learning Applied to Document Recognition Page. 7
Demo
Thank you
Yung-Kuei (Craig), Chen

Weitere ähnliche Inhalte

Was ist angesagt?

Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
milad abbasi
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
PyData
 

Was ist angesagt? (20)

Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)
 
Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
 
Modern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentationModern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentation
 
Image classification using cnn
Image classification using cnnImage classification using cnn
Image classification using cnn
 
Cnn method
Cnn methodCnn method
Cnn method
 
Convolutional Neural Network
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural Network
 
Cnn
CnnCnn
Cnn
 
Convolutional neural network
Convolutional neural network Convolutional neural network
Convolutional neural network
 
Cnn
CnnCnn
Cnn
 
CNN Machine learning DeepLearning
CNN Machine learning DeepLearningCNN Machine learning DeepLearning
CNN Machine learning DeepLearning
 
CONVOLUTIONAL NEURAL NETWORK
CONVOLUTIONAL NEURAL NETWORKCONVOLUTIONAL NEURAL NETWORK
CONVOLUTIONAL NEURAL NETWORK
 
Google net
Google netGoogle net
Google net
 
CNN and its applications by ketaki
CNN and its applications by ketakiCNN and its applications by ketaki
CNN and its applications by ketaki
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
 
Densenet CNN
Densenet CNNDensenet CNN
Densenet CNN
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
 
Mask R-CNN
Mask R-CNNMask R-CNN
Mask R-CNN
 

Ähnlich wie Convolutional Neural Network (CNN) - image recognition

[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
台灣資料科學年會
 
Deep Neural Network DNN.docx
Deep Neural Network DNN.docxDeep Neural Network DNN.docx
Deep Neural Network DNN.docx
jaffarbikat
 

Ähnlich wie Convolutional Neural Network (CNN) - image recognition (20)

convnets.pptx
convnets.pptxconvnets.pptx
convnets.pptx
 
introduction to deeplearning
introduction to deeplearningintroduction to deeplearning
introduction to deeplearning
 
Convolutional neural networks
Convolutional neural  networksConvolutional neural  networks
Convolutional neural networks
 
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
 
IRJET- Machine Learning based Object Identification System using Python
IRJET- Machine Learning based Object Identification System using PythonIRJET- Machine Learning based Object Identification System using Python
IRJET- Machine Learning based Object Identification System using Python
 
Web Spam Classification Using Supervised Artificial Neural Network Algorithms
Web Spam Classification Using Supervised Artificial Neural Network AlgorithmsWeb Spam Classification Using Supervised Artificial Neural Network Algorithms
Web Spam Classification Using Supervised Artificial Neural Network Algorithms
 
Deep Learning for Computer Vision - PyconDE 2017
Deep Learning for Computer Vision - PyconDE 2017Deep Learning for Computer Vision - PyconDE 2017
Deep Learning for Computer Vision - PyconDE 2017
 
Artificial Neural networks
Artificial Neural networksArtificial Neural networks
Artificial Neural networks
 
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep Learning
 
Deep Neural Network DNN.docx
Deep Neural Network DNN.docxDeep Neural Network DNN.docx
Deep Neural Network DNN.docx
 
What's Wrong With Deep Learning?
What's Wrong With Deep Learning?What's Wrong With Deep Learning?
What's Wrong With Deep Learning?
 
DL (v2).pptx
DL (v2).pptxDL (v2).pptx
DL (v2).pptx
 
Cnn
CnnCnn
Cnn
 
Autoencoders for image_classification
Autoencoders for image_classificationAutoencoders for image_classification
Autoencoders for image_classification
 
A Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware DetectionA Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware Detection
 
[系列活動] 一日搞懂生成式對抗網路
[系列活動] 一日搞懂生成式對抗網路[系列活動] 一日搞懂生成式對抗網路
[系列活動] 一日搞懂生成式對抗網路
 
Deep learning (2)
Deep learning (2)Deep learning (2)
Deep learning (2)
 
Web spam classification using supervised artificial neural network algorithms
Web spam classification using supervised artificial neural network algorithmsWeb spam classification using supervised artificial neural network algorithms
Web spam classification using supervised artificial neural network algorithms
 
Handwritten Digit Recognition using Convolutional Neural Networks
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural Networks
 

Kürzlich hochgeladen

Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
amitlee9823
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
shivangimorya083
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...
shambhavirathore45
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
amitlee9823
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
amitlee9823
 

Kürzlich hochgeladen (20)

Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptx
 
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort ServiceBDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfAccredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...Determinants of health, dimensions of health, positive health and spectrum of...
Determinants of health, dimensions of health, positive health and spectrum of...
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptx
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
 

Convolutional Neural Network (CNN) - image recognition

Hinweis der Redaktion

  1. Most of the features from convolutional and pooling layers may be good for the classification task, but combinations of those features might be even better