Introduction to CNN

Convolutional Neural Network
School of Computer Sicience and Engineering
1. Introduction
2. Convolution
3. Relu
4. Pooling
School of Computer Sicience and Engineering
3. Example by Tensorflow
1.1 Definition
• CNN is a specualized kind of neural network for processing
data thtat has a known, grid-like topology, such as time-
series(1D grid), image data(2D grid), etc.
• CNN is a supervised deep learning algorithm, it is used in
various fields like speech recognition, image retrieval and
face recognition.
School of Computer Sicience and Engineering
1.1 Definition
• ImageNet Classification with Deep Convolutional Neural Networks
(Cited by 9538, NIPS 2012, Alex Krizhevsky, Ilya Sutskever, Geoffrey
E. Hinton)
• build a CNN, has 60 million parameters and 650,000 neurons,
consists of five convolutional layers.
• Typical CNN is a 5 layer architecture consist of convolution layer,
pooling layer and classification layer.
• Convolution layer: extract the unique features from the input
image
• Pooling layer: reduce the dimensionality
• Generally CNN is trained using back-propagation algorithm
School of Computer Sicience and Engineering
1.2 Motivation
• MLP do not scale well
• MLP ignore pixel correlation
• MLP are not robust to image transformation
School of Computer Sicience and Engineering
multi-layer perceptron
2.1 Why Convolution ?
• preserves the spatial relationship
between pixels by learning image
features using small squares of
input data
• detect small,meaningful features
such as edges with kernels
School of Computer Sicience and Engineering
A 2D convolution example from deep learning book
2.2 Convolution Example
School of Computer Sicience and Engineering
input matrix
kernel matrix
2.2 Convolution Example
School of Computer Sicience and Engineering
different filters can detect
different features
2.2 Convolution Example
School of Computer Sicience and Engineering
The Convolution Operation
3 ReLU
• Introducing the Non Linearity
School of Computer Sicience and Engineering
Other non linear
functions such as
tanh or sigmoid can
also be used instead
of ReLU, but ReLU
has been found to
perform better in
most situations
4.1 Motivation of Pooling
• Reduce dimensionality
• In all cases, pooling helps to make the representation become
approximately invariant to small translations of the input.
• local translation can be a very useful property if we care more about
whether some feature is present than exactly where it is.
• Type of Pooling
• Max(works better)
• Average
• Sum
School of Computer Sicience and Engineering
4.2 Max Pooling
School of Computer Sicience and Engineering
5 Example by Tensorflow
School of Computer Sicience and Engineering
28 * 28
5 Example by Tensorflow
School of Computer Sicience and Engineering
5 Example by Tensorflow
School of Computer Sicience and Engineering
• zero-padding the 28x28x1 image to
32x32x1
• applying 5x5x32 convolution to get
28x28x32
• max-pooling down to 14x14x32 zero-
padding the 14x14x32 to 18x18x32
• applying 5x5x32x64 convolution to get
14x14x64
• max-pooling down to 7x7x64.
5 Example by Tensorflow
School of Computer Sicience and Engineering
Reference
• http://ufldl.stanford.edu/tutorial/supervised/ConvolutionalNeuralNetwork
• http://cs231n.github.io/convolutional-networks/
• https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/
• Deep Learning Book
• http://www.slideshare.net/ssuser06e0c5/explanation-on-tensorflow-
example-deep-mnist-for-expert
• http://shuaizhang.tech/2016/12/08/Tensorflow%E6%95%99%E7%A8%8B2
-Deep-MNIST-Using-CNN/
School of Computer Sicience and Engineering
School of Computer Sicience and Engineering
1 de 18

Recomendados

Convolutional Neural Network Models - Deep Learning por
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningBenha University
12.7K visualizações83 slides
Cnn por
CnnCnn
CnnNirthika Rajendran
14.1K visualizações31 slides
Machine Learning - Convolutional Neural Network por
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkRichard Kuo
1K visualizações36 slides
Convolutional Neural Network and Its Applications por
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsKasun Chinthaka Piyarathna
4.6K visualizações23 slides
Convolutional Neural Networks (CNN) por
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Gaurav Mittal
58.5K visualizações70 slides
Convolutional neural network por
Convolutional neural networkConvolutional neural network
Convolutional neural networkMojammilHusain
1.1K visualizações11 slides

Mais conteúdo relacionado

Mais procurados

Convolutional Neural Network (CNN) por
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Muhammad Haroon
847 visualizações16 slides
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S... por
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...Simplilearn
13.6K visualizações63 slides
Introduction to Deep Learning por
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
3.8K visualizações66 slides
Convolutional Neural Network (CNN) - image recognition por
Convolutional Neural Network (CNN)  - image recognitionConvolutional Neural Network (CNN)  - image recognition
Convolutional Neural Network (CNN) - image recognitionYUNG-KUEI CHEN
4.3K visualizações64 slides
Overview of Convolutional Neural Networks por
Overview of Convolutional Neural NetworksOverview of Convolutional Neural Networks
Overview of Convolutional Neural Networksananth
7.7K visualizações43 slides
Deep Learning - Overview of my work II por
Deep Learning - Overview of my work IIDeep Learning - Overview of my work II
Deep Learning - Overview of my work IIBenha University
15.6K visualizações59 slides

Mais procurados(20)

Convolutional Neural Network (CNN) por Muhammad Haroon
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
Muhammad Haroon847 visualizações
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S... por Simplilearn
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Simplilearn13.6K visualizações
Introduction to Deep Learning por Oswald Campesato
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
Oswald Campesato3.8K visualizações
Convolutional Neural Network (CNN) - image recognition por YUNG-KUEI CHEN
Convolutional Neural Network (CNN)  - image recognitionConvolutional Neural Network (CNN)  - image recognition
Convolutional Neural Network (CNN) - image recognition
YUNG-KUEI CHEN4.3K visualizações
Overview of Convolutional Neural Networks por ananth
Overview of Convolutional Neural NetworksOverview of Convolutional Neural Networks
Overview of Convolutional Neural Networks
ananth7.7K visualizações
Deep Learning - Overview of my work II por Benha University
Deep Learning - Overview of my work IIDeep Learning - Overview of my work II
Deep Learning - Overview of my work II
Benha University15.6K visualizações
Convolutional neural network por Yan Xu
Convolutional neural network Convolutional neural network
Convolutional neural network
Yan Xu5.3K visualizações
CNN Tutorial por Sungjoon Choi
CNN TutorialCNN Tutorial
CNN Tutorial
Sungjoon Choi5.6K visualizações
Convolutional neural network por Ferdous ahmed
Convolutional neural networkConvolutional neural network
Convolutional neural network
Ferdous ahmed555 visualizações
Convolutional Neural Network por Vignesh Suresh
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural Network
Vignesh Suresh268 visualizações
Convolution Neural Network (CNN) por Basit Rafiq
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
Basit Rafiq592 visualizações
CONVOLUTIONAL NEURAL NETWORK por Md Rajib Bhuiyan
CONVOLUTIONAL NEURAL NETWORKCONVOLUTIONAL NEURAL NETWORK
CONVOLUTIONAL NEURAL NETWORK
Md Rajib Bhuiyan711 visualizações
AlexNet por Bertil Hatt
AlexNetAlexNet
AlexNet
Bertil Hatt2.9K visualizações
Introduction to Deep learning por leopauly
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
leopauly1.7K visualizações
CNN and its applications by ketaki por Ketaki Patwari
CNN and its applications by ketakiCNN and its applications by ketaki
CNN and its applications by ketaki
Ketaki Patwari1.7K visualizações
Image classification using cnn por SumeraHangi
Image classification using cnnImage classification using cnn
Image classification using cnn
SumeraHangi741 visualizações
An introduction to Deep Learning por Julien SIMON
An introduction to Deep LearningAn introduction to Deep Learning
An introduction to Deep Learning
Julien SIMON4.3K visualizações
Cnn por Mehrnaz Faraz
CnnCnn
Cnn
Mehrnaz Faraz633 visualizações
Deep Learning Explained por Melanie Swan
Deep Learning ExplainedDeep Learning Explained
Deep Learning Explained
Melanie Swan41.4K visualizações
Deep learning por Benha University
Deep learningDeep learning
Deep learning
Benha University8.5K visualizações

Destaque

Convolution Neural Networks por
Convolution Neural NetworksConvolution Neural Networks
Convolution Neural NetworksAhmedMahany
14.2K visualizações9 slides
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015 por
Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015Jia-Bin Huang
16.5K visualizações76 slides
101: Convolutional Neural Networks por
101: Convolutional Neural Networks 101: Convolutional Neural Networks
101: Convolutional Neural Networks Mad Scientists
4K visualizações55 slides
Track2 02. machine intelligence at google scale google, kaz sato, staff devel... por
Track2 02. machine intelligence at google scale google, kaz sato, staff devel...Track2 02. machine intelligence at google scale google, kaz sato, staff devel...
Track2 02. machine intelligence at google scale google, kaz sato, staff devel...양 한빛
689 visualizações85 slides
Deep Convolutional Neural Networks - Overview por
Deep Convolutional Neural Networks - OverviewDeep Convolutional Neural Networks - Overview
Deep Convolutional Neural Networks - OverviewKeunwoo Choi
3.7K visualizações43 slides
Convolution codes - Coding/Decoding Tree codes and Trellis codes for multiple... por
Convolution codes - Coding/Decoding Tree codes and Trellis codes for multiple...Convolution codes - Coding/Decoding Tree codes and Trellis codes for multiple...
Convolution codes - Coding/Decoding Tree codes and Trellis codes for multiple...Madhumita Tamhane
40.6K visualizações98 slides

Destaque(20)

Convolution Neural Networks por AhmedMahany
Convolution Neural NetworksConvolution Neural Networks
Convolution Neural Networks
AhmedMahany14.2K visualizações
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015 por Jia-Bin Huang
Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
Jia-Bin Huang16.5K visualizações
101: Convolutional Neural Networks por Mad Scientists
101: Convolutional Neural Networks 101: Convolutional Neural Networks
101: Convolutional Neural Networks
Mad Scientists4K visualizações
Track2 02. machine intelligence at google scale google, kaz sato, staff devel... por 양 한빛
Track2 02. machine intelligence at google scale google, kaz sato, staff devel...Track2 02. machine intelligence at google scale google, kaz sato, staff devel...
Track2 02. machine intelligence at google scale google, kaz sato, staff devel...
양 한빛689 visualizações
Deep Convolutional Neural Networks - Overview por Keunwoo Choi
Deep Convolutional Neural Networks - OverviewDeep Convolutional Neural Networks - Overview
Deep Convolutional Neural Networks - Overview
Keunwoo Choi3.7K visualizações
Convolution codes - Coding/Decoding Tree codes and Trellis codes for multiple... por Madhumita Tamhane
Convolution codes - Coding/Decoding Tree codes and Trellis codes for multiple...Convolution codes - Coding/Decoding Tree codes and Trellis codes for multiple...
Convolution codes - Coding/Decoding Tree codes and Trellis codes for multiple...
Madhumita Tamhane40.6K visualizações
Case Study of Convolutional Neural Network por NamHyuk Ahn
Case Study of Convolutional Neural NetworkCase Study of Convolutional Neural Network
Case Study of Convolutional Neural Network
NamHyuk Ahn6.8K visualizações
Convolutional Neural Networks: Part 1 por ananth
Convolutional Neural Networks: Part 1Convolutional Neural Networks: Part 1
Convolutional Neural Networks: Part 1
ananth1.5K visualizações
Convolutional neural networks for image classification — evidence from Kaggle... por Dmytro Mishkin
Convolutional neural networks for image classification — evidence from Kaggle...Convolutional neural networks for image classification — evidence from Kaggle...
Convolutional neural networks for image classification — evidence from Kaggle...
Dmytro Mishkin4.8K visualizações
CNN Presentation por sacooke2
CNN PresentationCNN Presentation
CNN Presentation
sacooke210.2K visualizações
Deep Learning - Convolutional Neural Networks - Architectural Zoo por Christian Perone
Deep Learning - Convolutional Neural Networks - Architectural ZooDeep Learning - Convolutional Neural Networks - Architectural Zoo
Deep Learning - Convolutional Neural Networks - Architectural Zoo
Christian Perone26.2K visualizações
Introduction to XGboost por Shuai Zhang
Introduction to XGboostIntroduction to XGboost
Introduction to XGboost
Shuai Zhang4.9K visualizações
Intrusion Detection with Neural Networks por antoniomorancardenas
Intrusion Detection with Neural NetworksIntrusion Detection with Neural Networks
Intrusion Detection with Neural Networks
antoniomorancardenas3.9K visualizações
Convolutional Neural NetworkとRankNetを用いた画像の順序予測 por Shogo Suzuki
Convolutional Neural NetworkとRankNetを用いた画像の順序予測Convolutional Neural NetworkとRankNetを用いた画像の順序予測
Convolutional Neural NetworkとRankNetを用いた画像の順序予測
Shogo Suzuki784 visualizações
Deep Learning Survey por Anthony Parziale
Deep Learning SurveyDeep Learning Survey
Deep Learning Survey
Anthony Parziale768 visualizações
Understanding Convolutional Neural Networks por Jeremy Nixon
Understanding Convolutional Neural NetworksUnderstanding Convolutional Neural Networks
Understanding Convolutional Neural Networks
Jeremy Nixon1.4K visualizações
ujava.org Deep Learning with Convolutional Neural Network por 신동 강
ujava.org Deep Learning with Convolutional Neural Network ujava.org Deep Learning with Convolutional Neural Network
ujava.org Deep Learning with Convolutional Neural Network
신동 강1.4K visualizações
Ap Presentation por DEEPAKDEEPAK
Ap PresentationAp Presentation
Ap Presentation
DEEPAKDEEPAK528 visualizações
THINGS_YOU_WONT_SEE_ON_CNN por lounge
THINGS_YOU_WONT_SEE_ON_CNNTHINGS_YOU_WONT_SEE_ON_CNN
THINGS_YOU_WONT_SEE_ON_CNN
lounge2.9K visualizações

Similar a Introduction to CNN

Deep Learning por
Deep LearningDeep Learning
Deep LearningPierre de Lacaze
1.3K visualizações62 slides
DSRLab seminar Introduction to deep learning por
DSRLab seminar   Introduction to deep learningDSRLab seminar   Introduction to deep learning
DSRLab seminar Introduction to deep learningPoo Kuan Hoong
1.2K visualizações41 slides
intro-to-cnn-April_2020.pptx por
intro-to-cnn-April_2020.pptxintro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptxssuser3aa461
15 visualizações37 slides
A Survey of Convolutional Neural Networks por
A Survey of Convolutional Neural NetworksA Survey of Convolutional Neural Networks
A Survey of Convolutional Neural NetworksRimzim Thube
116 visualizações27 slides
Recurrent Neural Networks, LSTM and GRU por
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRUananth
29.8K visualizações38 slides
DL.pdf por
DL.pdfDL.pdf
DL.pdfssuserd23711
19 visualizações23 slides

Similar a Introduction to CNN(20)

Deep Learning por Pierre de Lacaze
Deep LearningDeep Learning
Deep Learning
Pierre de Lacaze1.3K visualizações
DSRLab seminar Introduction to deep learning por Poo Kuan Hoong
DSRLab seminar   Introduction to deep learningDSRLab seminar   Introduction to deep learning
DSRLab seminar Introduction to deep learning
Poo Kuan Hoong1.2K visualizações
intro-to-cnn-April_2020.pptx por ssuser3aa461
intro-to-cnn-April_2020.pptxintro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptx
ssuser3aa46115 visualizações
A Survey of Convolutional Neural Networks por Rimzim Thube
A Survey of Convolutional Neural NetworksA Survey of Convolutional Neural Networks
A Survey of Convolutional Neural Networks
Rimzim Thube116 visualizações
Recurrent Neural Networks, LSTM and GRU por ananth
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
ananth29.8K visualizações
DL.pdf por ssuserd23711
DL.pdfDL.pdf
DL.pdf
ssuserd2371119 visualizações
Autoencoders for image_classification por Cenk Bircanoğlu
Autoencoders for image_classificationAutoencoders for image_classification
Autoencoders for image_classification
Cenk Bircanoğlu4.9K visualizações
Neural Networks with Google TensorFlow por Darshan Patel
Neural Networks with Google TensorFlowNeural Networks with Google TensorFlow
Neural Networks with Google TensorFlow
Darshan Patel55.1K visualizações
Deep learning summary por ankit_ppt
Deep learning summaryDeep learning summary
Deep learning summary
ankit_ppt1.5K visualizações
Teach a neural network to read handwriting por Vipul Kaushal
Teach a neural network to read handwritingTeach a neural network to read handwriting
Teach a neural network to read handwriting
Vipul Kaushal46 visualizações
cnn.pdf por Amnaalia
cnn.pdfcnn.pdf
cnn.pdf
Amnaalia19 visualizações
CNN.pptx.pdf por Knoldus Inc.
CNN.pptx.pdfCNN.pptx.pdf
CNN.pptx.pdf
Knoldus Inc.35 visualizações
Tsinghua invited talk_zhou_xing_v2r0 por Joe Xing
Tsinghua invited talk_zhou_xing_v2r0Tsinghua invited talk_zhou_xing_v2r0
Tsinghua invited talk_zhou_xing_v2r0
Joe Xing271 visualizações
Introduction to deep learning por Amr Rashed
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
Amr Rashed370 visualizações
NVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflow por NVIDIA Taiwan
NVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflowNVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflow
NVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflow
NVIDIA Taiwan1.7K visualizações
DyCode Engineering - Machine Learning with TensorFlow por Alwin Arrasyid
DyCode Engineering - Machine Learning with TensorFlowDyCode Engineering - Machine Learning with TensorFlow
DyCode Engineering - Machine Learning with TensorFlow
Alwin Arrasyid142 visualizações
Convolutional neural networks 이론과 응용 por 홍배 김
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
홍배 김2.2K visualizações
Artificial Intelligence, Machine Learning and Deep Learning por Sujit Pal
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep Learning
Sujit Pal22.9K visualizações
Neural Networks in Data Mining - “An Overview” por Dr.(Mrs).Gethsiyal Augasta
Neural Networks  in Data Mining -   “An Overview”Neural Networks  in Data Mining -   “An Overview”
Neural Networks in Data Mining - “An Overview”
Dr.(Mrs).Gethsiyal Augasta283 visualizações
Deep learning - a primer por Uwe Friedrichsen
Deep learning - a primerDeep learning - a primer
Deep learning - a primer
Uwe Friedrichsen2.8K visualizações

Mais de Shuai Zhang

Introduction to Random Walk por
Introduction to Random WalkIntroduction to Random Walk
Introduction to Random WalkShuai Zhang
4.2K visualizações36 slides
Learning group variational inference por
Learning group  variational inferenceLearning group  variational inference
Learning group variational inferenceShuai Zhang
304 visualizações21 slides
Reading group nfm - 20170312 por
Reading group  nfm - 20170312Reading group  nfm - 20170312
Reading group nfm - 20170312Shuai Zhang
124 visualizações25 slides
Talk@rmit 09112017 por
Talk@rmit 09112017Talk@rmit 09112017
Talk@rmit 09112017Shuai Zhang
660 visualizações50 slides
Learning group em - 20171025 - copy por
Learning group   em - 20171025 - copyLearning group   em - 20171025 - copy
Learning group em - 20171025 - copyShuai Zhang
154 visualizações34 slides
Learning group dssm - 20170605 por
Learning group   dssm - 20170605Learning group   dssm - 20170605
Learning group dssm - 20170605Shuai Zhang
461 visualizações20 slides

Mais de Shuai Zhang(7)

Introduction to Random Walk por Shuai Zhang
Introduction to Random WalkIntroduction to Random Walk
Introduction to Random Walk
Shuai Zhang4.2K visualizações
Learning group variational inference por Shuai Zhang
Learning group  variational inferenceLearning group  variational inference
Learning group variational inference
Shuai Zhang304 visualizações
Reading group nfm - 20170312 por Shuai Zhang
Reading group  nfm - 20170312Reading group  nfm - 20170312
Reading group nfm - 20170312
Shuai Zhang124 visualizações
Talk@rmit 09112017 por Shuai Zhang
Talk@rmit 09112017Talk@rmit 09112017
Talk@rmit 09112017
Shuai Zhang660 visualizações
Learning group em - 20171025 - copy por Shuai Zhang
Learning group   em - 20171025 - copyLearning group   em - 20171025 - copy
Learning group em - 20171025 - copy
Shuai Zhang154 visualizações
Learning group dssm - 20170605 por Shuai Zhang
Learning group   dssm - 20170605Learning group   dssm - 20170605
Learning group dssm - 20170605
Shuai Zhang461 visualizações
Reading group gan - 20170417 por Shuai Zhang
Reading group   gan - 20170417Reading group   gan - 20170417
Reading group gan - 20170417
Shuai Zhang462 visualizações

Último

The Power of Generative AI in Accelerating No Code Adoption.pdf por
The Power of Generative AI in Accelerating No Code Adoption.pdfThe Power of Generative AI in Accelerating No Code Adoption.pdf
The Power of Generative AI in Accelerating No Code Adoption.pdfSaeed Al Dhaheri
32 visualizações18 slides
CryptoBotsAI por
CryptoBotsAICryptoBotsAI
CryptoBotsAIchandureddyvadala199
40 visualizações5 slides
Why and How CloudStack at weSystems - Stephan Bienek - weSystems por
Why and How CloudStack at weSystems - Stephan Bienek - weSystemsWhy and How CloudStack at weSystems - Stephan Bienek - weSystems
Why and How CloudStack at weSystems - Stephan Bienek - weSystemsShapeBlue
238 visualizações13 slides
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti... por
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...ShapeBlue
139 visualizações29 slides
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading... por
Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading...The Digital Insurer
90 visualizações52 slides
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit... por
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...ShapeBlue
159 visualizações25 slides

Último(20)

The Power of Generative AI in Accelerating No Code Adoption.pdf por Saeed Al Dhaheri
The Power of Generative AI in Accelerating No Code Adoption.pdfThe Power of Generative AI in Accelerating No Code Adoption.pdf
The Power of Generative AI in Accelerating No Code Adoption.pdf
Saeed Al Dhaheri32 visualizações
Why and How CloudStack at weSystems - Stephan Bienek - weSystems por ShapeBlue
Why and How CloudStack at weSystems - Stephan Bienek - weSystemsWhy and How CloudStack at weSystems - Stephan Bienek - weSystems
Why and How CloudStack at weSystems - Stephan Bienek - weSystems
ShapeBlue238 visualizações
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti... por ShapeBlue
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...
ShapeBlue139 visualizações
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading... por The Digital Insurer
Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading...
The Digital Insurer90 visualizações
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit... por ShapeBlue
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
ShapeBlue159 visualizações
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue por ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlueCloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
ShapeBlue138 visualizações
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT por ShapeBlue
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBITUpdates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
ShapeBlue206 visualizações
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f... por TrustArc
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc170 visualizações
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ... por ShapeBlue
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ...How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ...
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ...
ShapeBlue166 visualizações
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P... por ShapeBlue
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
ShapeBlue194 visualizações
Hypervisor Agnostic DRS in CloudStack - Brief overview & demo - Vishesh Jinda... por ShapeBlue
Hypervisor Agnostic DRS in CloudStack - Brief overview & demo - Vishesh Jinda...Hypervisor Agnostic DRS in CloudStack - Brief overview & demo - Vishesh Jinda...
Hypervisor Agnostic DRS in CloudStack - Brief overview & demo - Vishesh Jinda...
ShapeBlue161 visualizações
Digital Personal Data Protection (DPDP) Practical Approach For CISOs por Priyanka Aash
Digital Personal Data Protection (DPDP) Practical Approach For CISOsDigital Personal Data Protection (DPDP) Practical Approach For CISOs
Digital Personal Data Protection (DPDP) Practical Approach For CISOs
Priyanka Aash158 visualizações
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha... por ShapeBlue
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...
ShapeBlue180 visualizações
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue por ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
ShapeBlue147 visualizações
Future of AR - Facebook Presentation por Rob McCarty
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook Presentation
Rob McCarty64 visualizações
Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or... por ShapeBlue
Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or...Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or...
Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or...
ShapeBlue198 visualizações
Transcript: Redefining the book supply chain: A glimpse into the future - Tec... por BookNet Canada
Transcript: Redefining the book supply chain: A glimpse into the future - Tec...Transcript: Redefining the book supply chain: A glimpse into the future - Tec...
Transcript: Redefining the book supply chain: A glimpse into the future - Tec...
BookNet Canada41 visualizações
Live Demo Showcase: Unveiling Dell PowerFlex’s IaaS Capabilities with Apache ... por ShapeBlue
Live Demo Showcase: Unveiling Dell PowerFlex’s IaaS Capabilities with Apache ...Live Demo Showcase: Unveiling Dell PowerFlex’s IaaS Capabilities with Apache ...
Live Demo Showcase: Unveiling Dell PowerFlex’s IaaS Capabilities with Apache ...
ShapeBlue126 visualizações
Initiating and Advancing Your Strategic GIS Governance Strategy por Safe Software
Initiating and Advancing Your Strategic GIS Governance StrategyInitiating and Advancing Your Strategic GIS Governance Strategy
Initiating and Advancing Your Strategic GIS Governance Strategy
Safe Software176 visualizações

Introduction to CNN

  • 1. Convolutional Neural Network School of Computer Sicience and Engineering
  • 2. 1. Introduction 2. Convolution 3. Relu 4. Pooling School of Computer Sicience and Engineering 3. Example by Tensorflow
  • 3. 1.1 Definition • CNN is a specualized kind of neural network for processing data thtat has a known, grid-like topology, such as time- series(1D grid), image data(2D grid), etc. • CNN is a supervised deep learning algorithm, it is used in various fields like speech recognition, image retrieval and face recognition. School of Computer Sicience and Engineering
  • 4. 1.1 Definition • ImageNet Classification with Deep Convolutional Neural Networks (Cited by 9538, NIPS 2012, Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton) • build a CNN, has 60 million parameters and 650,000 neurons, consists of five convolutional layers. • Typical CNN is a 5 layer architecture consist of convolution layer, pooling layer and classification layer. • Convolution layer: extract the unique features from the input image • Pooling layer: reduce the dimensionality • Generally CNN is trained using back-propagation algorithm School of Computer Sicience and Engineering
  • 5. 1.2 Motivation • MLP do not scale well • MLP ignore pixel correlation • MLP are not robust to image transformation School of Computer Sicience and Engineering multi-layer perceptron
  • 6. 2.1 Why Convolution ? • preserves the spatial relationship between pixels by learning image features using small squares of input data • detect small,meaningful features such as edges with kernels School of Computer Sicience and Engineering A 2D convolution example from deep learning book
  • 7. 2.2 Convolution Example School of Computer Sicience and Engineering input matrix kernel matrix
  • 8. 2.2 Convolution Example School of Computer Sicience and Engineering different filters can detect different features
  • 9. 2.2 Convolution Example School of Computer Sicience and Engineering The Convolution Operation
  • 10. 3 ReLU • Introducing the Non Linearity School of Computer Sicience and Engineering Other non linear functions such as tanh or sigmoid can also be used instead of ReLU, but ReLU has been found to perform better in most situations
  • 11. 4.1 Motivation of Pooling • Reduce dimensionality • In all cases, pooling helps to make the representation become approximately invariant to small translations of the input. • local translation can be a very useful property if we care more about whether some feature is present than exactly where it is. • Type of Pooling • Max(works better) • Average • Sum School of Computer Sicience and Engineering
  • 12. 4.2 Max Pooling School of Computer Sicience and Engineering
  • 13. 5 Example by Tensorflow School of Computer Sicience and Engineering 28 * 28
  • 14. 5 Example by Tensorflow School of Computer Sicience and Engineering
  • 15. 5 Example by Tensorflow School of Computer Sicience and Engineering • zero-padding the 28x28x1 image to 32x32x1 • applying 5x5x32 convolution to get 28x28x32 • max-pooling down to 14x14x32 zero- padding the 14x14x32 to 18x18x32 • applying 5x5x32x64 convolution to get 14x14x64 • max-pooling down to 7x7x64.
  • 16. 5 Example by Tensorflow School of Computer Sicience and Engineering
  • 17. Reference • http://ufldl.stanford.edu/tutorial/supervised/ConvolutionalNeuralNetwork • http://cs231n.github.io/convolutional-networks/ • https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/ • Deep Learning Book • http://www.slideshare.net/ssuser06e0c5/explanation-on-tensorflow- example-deep-mnist-for-expert • http://shuaizhang.tech/2016/12/08/Tensorflow%E6%95%99%E7%A8%8B2 -Deep-MNIST-Using-CNN/ School of Computer Sicience and Engineering
  • 18. School of Computer Sicience and Engineering

Notas do Editor

  1. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  2. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  3. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  4. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  5. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  6. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  7. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  8. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  9. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  10. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)
  11. For example, when determining whether an image contains a face, we need not know the location of the eyes with pixel-perfect accuracy, we just need to know that there is an eye on the left side of the face and an eye on the right side of the face
  12. For example, when determining whether an image contains a face, we need not know the location of the eyes with pixel-perfect accuracy, we just need to know that there is an eye on the left side of the face and an eye on the right side of the face
  13. For example, when determining whether an image contains a face, we need not know the location of the eyes with pixel-perfect accuracy, we just need to know that there is an eye on the left side of the face and an eye on the right side of the face
  14. For example, when determining whether an image contains a face, we need not know the location of the eyes with pixel-perfect accuracy, we just need to know that there is an eye on the left side of the face and an eye on the right side of the face
  15. For example, when determining whether an image contains a face, we need not know the location of the eyes with pixel-perfect accuracy, we just need to know that there is an eye on the left side of the face and an eye on the right side of the face
  16. For example, when determining whether an image contains a face, we need not know the location of the eyes with pixel-perfect accuracy, we just need to know that there is an eye on the left side of the face and an eye on the right side of the face
  17. For example, when determining whether an image contains a face, we need not know the location of the eyes with pixel-perfect accuracy, we just need to know that there is an eye on the left side of the face and an eye on the right side of the face
  18. \hat{r} = u + b_u +b_i + p_u^T(q_i+\epsilon)