SlideShare ist ein Scribd-Unternehmen logo
DATA SCIENCE
2
C o n v o l u t i o n a l N e u r a l N e t w o r k
Field of
Artificial Intelligence
Field of
M achine Learning
Bangladesh University of Professionals(BUP)
Deep Learning
3
Bangladesh University of Professionals(BUP)
C o n v o l u t i o n a l N e u r a l N e t w o r k
Input Classification
Feature Extraction
Car
Not Car
Output
Input Feature Extraction + Classification
Car
Not Car
Output
Deep Learning
Machine Learning
4
Bangladesh University of Professionals(BUP)
C o n v o l u t i o n a l N e u r a l N e t w o r k
Neural Network
As like as Human Neuron Network
5
Bangladesh University of Professionals(BUP)
C o n v o l u t i o n a l N e u r a l N e t w o r k
Neural Network
Artificial Neural Network
(ANN)
Regression and Classification
Convolutional Neural Network
(CNN)
Computer Vision
Recurrent Neural Network
(RNN)
Time Series Analysis
AN
N
6
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
CN
N
RN
N
7
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Application of CNN
Convolutional Neural Networks CNNs have the potentials to
revolutionize many industries and improve our daily life. CNN have a
wide range of applications. Such as:
 Object detection.
 Face Recognition.
 Medical Imaging.
 Analyzing Documents.
 Understanding Climate.
 Grey Areas.
 Advertising.
 Self Driving Car.
 Security Systems.
C o n v o l u t i o n a l N e u r a l N e t w o r k
8
snow covered ground, a blue and a white jacket,
a black and a gray jacket, two people standing
on skis, woman wearing a blue jacket, a blue
helmet, a blue helmet on the head, blue jeans on
the girl, a man and a snow covered mountain, a
ski lift, white snow on the ground, trees covered
in snow, a tree with no leaves.
Optical Character Recognition is
designed to convert your
handwriting into text.
Bangladesh University of Professionals(BUP)
Application
s
Bangladesh University of Professionals(BUP)
1 0
Bangladesh University of Professionals(BUP)
C o n v o l u t i o n a l N e u r a l N e t w o r k
Convolutional Neural Networks (CNN) learns multilevel features
and classifier in a joint fashion and performs much better than
traditional approaches for various image classification and
segmentation problems.
Introduction
11
Bangladesh University of Professionals(BUP)
C o n v o l u t i o n a l N e u r a l N e t w o r k
CNN – What do they learn?
CNN - Components
There are four main components in the CNN:
1. Convolutional
2. Non-Linearity
3. Pooling or Sub Sampling
4. Classification (Fully Connected Layer)​
1 2
Bangladesh University of Professionals(BUP)
C o n v o l u t i o n a l N e u r a l N e t w o r k
1 3
Bangladesh University of Professionals(BUP)
C o n v o l u t i o n a l N e u r a l N e t w o r k
Input
An image is a matrix of pixel
values.
If we consider a RGB image, each
pixel will have the combined values
of R, G and B.
If we consider a gray scale image,
the value of each pixel in the
matrix will range from 0 to 255.
What we see!!! What Computer See!!!
1 4
Bangladesh University of Professionals(BUP)
C o n v o l u t i o n a l N e u r a l N e t w o r k
Convolutional
The primary purpose of Convolutional in case of CNN is to
extract features from the input image.
0
0
0
0
1
1
1
1
1
4 Filter / Kernel / Feature Detector
Convolved Features /
Activation Map /
Feature Map
Image
0
0
0
1
0
0
1
1
1
1
0
0 0
0 1 1
1X1
1X1
1X1
1X0
1X0
1X1
0X0
0X0
0X1
1 5
Bangladesh University of Professionals(BUP)
C o n v o l u t i o n a l N e u r a l N e t w o r k
Convolutional…
Input Image
• The size of the output volume is controlled by three parameters that we need
to decide before the convolutional step is performed:
1 6
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Convolutional…
 Depth: Depth corresponds to the number of filters we use for the convolutional
operation.
 Stride: Stride is the number of pixels by which we slide our filter matrix over the
input matrix.
 Zero-padding: Sometimes, it is convenient to pad the input matrix with zeros
around the border, so that we can apply the filter to bordering elements of our input
image matrix.
 With zero-padding wide convolutional
 Without zero-padding narrow convolutional
1 7
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Non-Linearity (ReLU)
• Replaces all negative pixel values in the feature
map by zero.
• The purpose of ReLU is to introduce non-linearity
in CNN, since most of the real world data would
be non-linear.
• Other non-linear functions such as tanh (-1,1) or
sigmoid (0,1) can also be used instead of ReLU
(0,input)
23
18
75
101
0
25
0
20
100
25
0
35
18
0
20
15
15 20 -10 35
25
18 -110
-15 -10
20
23
18
75
101
25 100
Transfer Function
0,0
1 8
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Pooling
Reduces the dimensionality of each feature map but retains the most important
information. Pooling can be different types: Max, Average, Sum etc.
4
1
2
4
3
2
5
5
1
4
9
7
2
3
1
8 8
9
7
2x2 region
1 9
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Story so far…..
• Together these layers extract the useful features from the images.
• The output from the convolutional and pooling layers represent high-level
features of the input image.
High-level features
Feature extraction
2x2
Subsampling
5x5
Convolution
2x2
Subsampling
5x5
Convolution
input
32x32
C1
feature maps
28x28
S1
feature maps
14x14
C2
feature maps
10x10
2 0
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Fully Connected Layer
• A traditional Multi-layer Perceptron.
• The term “Fully-Connected” implies that every neuron in the previous layer is
connected to every neuron on the next layer.
• Their activations can hence be computed with a matrix multiplication followed
by a bias offset.
• The purpose of the fully connected layer is to use the high level features for
classifying the input image into various classes based on the training dataset.
2 1
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Fully Connected Layer
2 2
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Fully Connected Layer
2 3
2 4
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Overall CNN Architecture
Feature extraction
2x2
Subsampling
5x5
Convolution
2x2
Subsampling
5x5
Convolution
input
32x32
C1
feature maps
28x28
S1
feature maps
14x14
C2
feature maps
10x10
S2
feature maps
5x5
n1
n2
output
Classification
Fully
Connected
0
1
8
9
2 5
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Putting it all together – Training using Backpropagation
Step-3: Calculate the total error at the output layer (summation over all 4
classes).
Step-2: The network takes a training Image as input, goes through the
forward propagation step (convolutional, ReLU and pooling operations
along with forward propagation in the fully connected layer) and find the
output probabilities for each class.
Step-1: We initialize all filters and parameters / weights with random
values.
• Let’s say the output probabilities for the boat image above are [0.2,0.4,0.1,0.3].
• Since weight are randomly assigned for the first training example, output
probabilities are also random.
2 6
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Step-4: Use Backpropagation to calculate the gradients of the error with
respect to all weights in the network and use gradient descent to update
all filter values/weights and parameter values to minimize the output
error.
• The weights are adjusted in proportion to their contribution to the total error.
• When the same image is input again, output probabilities might now be
[0.1, 0.1, 0.7, 0.1], which is closer to the target vector [0, 0, 1, 0].
• This means that the network has learnt to classify this particular image correctly
by adjusting its weights / filters such that the output error is reduced.
• Parameters like number of filters, filter sizes, architecture of the network etc.
have all been fixed before Step 1 and do not change during training process -
only the values of the filter matrix and connection weights get updated.
Step-5: Repeat steps 2-4 with all images in the training set.
2 7
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Types of
CNN Architectures
2 8
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Year CNN Architecture Developed By
1998 LeNet Yann LeCun et al.
2012 AlexNet Alex Krizhevsky, Geoffrey Hinton and Ilya Sutskever
2013 ZFNet Matthew Zeiler and Rob Fergus
2014 GoogleNet Google
2014 VGGNet Simonyan and Zisserman
2015 ResNet Kaiming He
2017 DenseNet Gao Huang, Zhuang Liu, Laurens van der Maaten and Killian Q.Weinberger
2 9
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
GoogleNet
3 0
C o n v o l u t i o n a l N e u r a l N e t w o r k
Bangladesh University of Professionals(BUP)
Limitation
CNNs also have some drawbacks that limit their performance and
applicability. One of the main disadvantages of CNNs is that they require
a large amount of labeled data to train effectively, which can be costly and
time-consuming to obtain and annotate.
Coordinate Frame
Classification of Images with
different Positions
Illustrates the dismantled
components of a face
Convolutional Neural Networks CNN

Weitere ähnliche Inhalte

Ähnlich wie Convolutional Neural Networks CNN

Parallel k nn on gpu architecture using opencl
Parallel k nn on gpu architecture using openclParallel k nn on gpu architecture using opencl
Parallel k nn on gpu architecture using opencl
eSAT Publishing House
 
Parallel knn on gpu architecture using opencl
Parallel knn on gpu architecture using openclParallel knn on gpu architecture using opencl
Parallel knn on gpu architecture using opencl
eSAT Journals
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
Hiroshi Fukui
 
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET Journal
 
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
csandit
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
David Dao
 
Deep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistryDeep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistry
Kenta Oono
 
IRJET- Identification of Scene Images using Convolutional Neural Networks - A...
IRJET- Identification of Scene Images using Convolutional Neural Networks - A...IRJET- Identification of Scene Images using Convolutional Neural Networks - A...
IRJET- Identification of Scene Images using Convolutional Neural Networks - A...
IRJET Journal
 
Plant Disease Detection using Convolution Neural Network (CNN)
Plant Disease Detection using Convolution Neural Network (CNN)Plant Disease Detection using Convolution Neural Network (CNN)
Plant Disease Detection using Convolution Neural Network (CNN)
IRJET Journal
 
Face recognition using gaussian mixture model & artificial neural network
Face recognition using gaussian mixture model & artificial neural networkFace recognition using gaussian mixture model & artificial neural network
Face recognition using gaussian mixture model & artificial neural network
eSAT Journals
 
DEEP LEARNING BASED BRAIN STROKE DETECTION
DEEP LEARNING BASED BRAIN STROKE DETECTIONDEEP LEARNING BASED BRAIN STROKE DETECTION
DEEP LEARNING BASED BRAIN STROKE DETECTION
IRJET Journal
 
Scene understanding
Scene understandingScene understanding
Scene understanding
Mohammed Shoaib
 
Human age and gender Detection
Human age and gender DetectionHuman age and gender Detection
Human age and gender Detection
AbhiAchalla
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
ParrotAI
 
Real Time Sign Language Recognition Using Deep Learning
Real Time Sign Language Recognition Using Deep LearningReal Time Sign Language Recognition Using Deep Learning
Real Time Sign Language Recognition Using Deep Learning
IRJET Journal
 
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting PneumoniaIRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET Journal
 
IRJET- Implementation of Gender Detection with Notice Board using Raspberry Pi
IRJET- Implementation of Gender Detection with Notice Board using Raspberry PiIRJET- Implementation of Gender Detection with Notice Board using Raspberry Pi
IRJET- Implementation of Gender Detection with Notice Board using Raspberry Pi
IRJET Journal
 
Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.
IRJET Journal
 
Classification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its VariantsClassification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its Variants
IRJET Journal
 
Lung Cancer Detection Using Convolutional Neural Network
Lung Cancer Detection Using Convolutional Neural NetworkLung Cancer Detection Using Convolutional Neural Network
Lung Cancer Detection Using Convolutional Neural Network
IRJET Journal
 

Ähnlich wie Convolutional Neural Networks CNN (20)

Parallel k nn on gpu architecture using opencl
Parallel k nn on gpu architecture using openclParallel k nn on gpu architecture using opencl
Parallel k nn on gpu architecture using opencl
 
Parallel knn on gpu architecture using opencl
Parallel knn on gpu architecture using openclParallel knn on gpu architecture using opencl
Parallel knn on gpu architecture using opencl
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
 
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
 
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
 
Deep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistryDeep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistry
 
IRJET- Identification of Scene Images using Convolutional Neural Networks - A...
IRJET- Identification of Scene Images using Convolutional Neural Networks - A...IRJET- Identification of Scene Images using Convolutional Neural Networks - A...
IRJET- Identification of Scene Images using Convolutional Neural Networks - A...
 
Plant Disease Detection using Convolution Neural Network (CNN)
Plant Disease Detection using Convolution Neural Network (CNN)Plant Disease Detection using Convolution Neural Network (CNN)
Plant Disease Detection using Convolution Neural Network (CNN)
 
Face recognition using gaussian mixture model & artificial neural network
Face recognition using gaussian mixture model & artificial neural networkFace recognition using gaussian mixture model & artificial neural network
Face recognition using gaussian mixture model & artificial neural network
 
DEEP LEARNING BASED BRAIN STROKE DETECTION
DEEP LEARNING BASED BRAIN STROKE DETECTIONDEEP LEARNING BASED BRAIN STROKE DETECTION
DEEP LEARNING BASED BRAIN STROKE DETECTION
 
Scene understanding
Scene understandingScene understanding
Scene understanding
 
Human age and gender Detection
Human age and gender DetectionHuman age and gender Detection
Human age and gender Detection
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
 
Real Time Sign Language Recognition Using Deep Learning
Real Time Sign Language Recognition Using Deep LearningReal Time Sign Language Recognition Using Deep Learning
Real Time Sign Language Recognition Using Deep Learning
 
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting PneumoniaIRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
 
IRJET- Implementation of Gender Detection with Notice Board using Raspberry Pi
IRJET- Implementation of Gender Detection with Notice Board using Raspberry PiIRJET- Implementation of Gender Detection with Notice Board using Raspberry Pi
IRJET- Implementation of Gender Detection with Notice Board using Raspberry Pi
 
Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.
 
Classification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its VariantsClassification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its Variants
 
Lung Cancer Detection Using Convolutional Neural Network
Lung Cancer Detection Using Convolutional Neural NetworkLung Cancer Detection Using Convolutional Neural Network
Lung Cancer Detection Using Convolutional Neural Network
 

Mehr von Abdullah al Mamun

Underfitting and Overfitting in Machine Learning
Underfitting and Overfitting in Machine LearningUnderfitting and Overfitting in Machine Learning
Underfitting and Overfitting in Machine Learning
Abdullah al Mamun
 
Recurrent Neural Networks (RNNs)
Recurrent Neural Networks (RNNs)Recurrent Neural Networks (RNNs)
Recurrent Neural Networks (RNNs)
Abdullah al Mamun
 
Random Forest
Random ForestRandom Forest
Random Forest
Abdullah al Mamun
 
Principal Component Analysis PCA
Principal Component Analysis PCAPrincipal Component Analysis PCA
Principal Component Analysis PCA
Abdullah al Mamun
 
Natural Language Processing (NLP)
Natural Language Processing (NLP)Natural Language Processing (NLP)
Natural Language Processing (NLP)
Abdullah al Mamun
 
Naive Bayes
Naive BayesNaive Bayes
Naive Bayes
Abdullah al Mamun
 
Multilayer Perceptron Neural Network MLP
Multilayer Perceptron Neural Network MLPMultilayer Perceptron Neural Network MLP
Multilayer Perceptron Neural Network MLP
Abdullah al Mamun
 
Long Short Term Memory LSTM
Long Short Term Memory LSTMLong Short Term Memory LSTM
Long Short Term Memory LSTM
Abdullah al Mamun
 
Linear Regression
Linear RegressionLinear Regression
Linear Regression
Abdullah al Mamun
 
K-Nearest Neighbor(KNN)
K-Nearest Neighbor(KNN)K-Nearest Neighbor(KNN)
K-Nearest Neighbor(KNN)
Abdullah al Mamun
 
Hidden Markov Model (HMM)
Hidden Markov Model (HMM)Hidden Markov Model (HMM)
Hidden Markov Model (HMM)
Abdullah al Mamun
 
Ensemble Method (Bagging Boosting)
Ensemble Method (Bagging Boosting)Ensemble Method (Bagging Boosting)
Ensemble Method (Bagging Boosting)
Abdullah al Mamun
 
Artificial Neural Network ANN
Artificial Neural Network ANNArtificial Neural Network ANN
Artificial Neural Network ANN
Abdullah al Mamun
 
Reinforcement Learning, Application and Q-Learning
Reinforcement Learning, Application and Q-LearningReinforcement Learning, Application and Q-Learning
Reinforcement Learning, Application and Q-Learning
Abdullah al Mamun
 
Session on evaluation of DevSecOps
Session on evaluation of DevSecOpsSession on evaluation of DevSecOps
Session on evaluation of DevSecOps
Abdullah al Mamun
 
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
Abdullah al Mamun
 
DevOps Presentation.pptx
DevOps Presentation.pptxDevOps Presentation.pptx
DevOps Presentation.pptx
Abdullah al Mamun
 
Python Virtual Environment.pptx
Python Virtual Environment.pptxPython Virtual Environment.pptx
Python Virtual Environment.pptx
Abdullah al Mamun
 
Artificial intelligence Presentation.pptx
Artificial intelligence Presentation.pptxArtificial intelligence Presentation.pptx
Artificial intelligence Presentation.pptx
Abdullah al Mamun
 
An approach to empirical Optical Character recognition paradigm using Multi-L...
An approach to empirical Optical Character recognition paradigm using Multi-L...An approach to empirical Optical Character recognition paradigm using Multi-L...
An approach to empirical Optical Character recognition paradigm using Multi-L...
Abdullah al Mamun
 

Mehr von Abdullah al Mamun (20)

Underfitting and Overfitting in Machine Learning
Underfitting and Overfitting in Machine LearningUnderfitting and Overfitting in Machine Learning
Underfitting and Overfitting in Machine Learning
 
Recurrent Neural Networks (RNNs)
Recurrent Neural Networks (RNNs)Recurrent Neural Networks (RNNs)
Recurrent Neural Networks (RNNs)
 
Random Forest
Random ForestRandom Forest
Random Forest
 
Principal Component Analysis PCA
Principal Component Analysis PCAPrincipal Component Analysis PCA
Principal Component Analysis PCA
 
Natural Language Processing (NLP)
Natural Language Processing (NLP)Natural Language Processing (NLP)
Natural Language Processing (NLP)
 
Naive Bayes
Naive BayesNaive Bayes
Naive Bayes
 
Multilayer Perceptron Neural Network MLP
Multilayer Perceptron Neural Network MLPMultilayer Perceptron Neural Network MLP
Multilayer Perceptron Neural Network MLP
 
Long Short Term Memory LSTM
Long Short Term Memory LSTMLong Short Term Memory LSTM
Long Short Term Memory LSTM
 
Linear Regression
Linear RegressionLinear Regression
Linear Regression
 
K-Nearest Neighbor(KNN)
K-Nearest Neighbor(KNN)K-Nearest Neighbor(KNN)
K-Nearest Neighbor(KNN)
 
Hidden Markov Model (HMM)
Hidden Markov Model (HMM)Hidden Markov Model (HMM)
Hidden Markov Model (HMM)
 
Ensemble Method (Bagging Boosting)
Ensemble Method (Bagging Boosting)Ensemble Method (Bagging Boosting)
Ensemble Method (Bagging Boosting)
 
Artificial Neural Network ANN
Artificial Neural Network ANNArtificial Neural Network ANN
Artificial Neural Network ANN
 
Reinforcement Learning, Application and Q-Learning
Reinforcement Learning, Application and Q-LearningReinforcement Learning, Application and Q-Learning
Reinforcement Learning, Application and Q-Learning
 
Session on evaluation of DevSecOps
Session on evaluation of DevSecOpsSession on evaluation of DevSecOps
Session on evaluation of DevSecOps
 
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
Artificial Intelligence: Classification, Applications, Opportunities, and Cha...
 
DevOps Presentation.pptx
DevOps Presentation.pptxDevOps Presentation.pptx
DevOps Presentation.pptx
 
Python Virtual Environment.pptx
Python Virtual Environment.pptxPython Virtual Environment.pptx
Python Virtual Environment.pptx
 
Artificial intelligence Presentation.pptx
Artificial intelligence Presentation.pptxArtificial intelligence Presentation.pptx
Artificial intelligence Presentation.pptx
 
An approach to empirical Optical Character recognition paradigm using Multi-L...
An approach to empirical Optical Character recognition paradigm using Multi-L...An approach to empirical Optical Character recognition paradigm using Multi-L...
An approach to empirical Optical Character recognition paradigm using Multi-L...
 

Kürzlich hochgeladen

A presentation that explain the Power BI Licensing
A presentation that explain the Power BI LicensingA presentation that explain the Power BI Licensing
A presentation that explain the Power BI Licensing
AlessioFois2
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
Bill641377
 
Open Source Contributions to Postgres: The Basics POSETTE 2024
Open Source Contributions to Postgres: The Basics POSETTE 2024Open Source Contributions to Postgres: The Basics POSETTE 2024
Open Source Contributions to Postgres: The Basics POSETTE 2024
ElizabethGarrettChri
 
writing report business partner b1+ .pdf
writing report business partner b1+ .pdfwriting report business partner b1+ .pdf
writing report business partner b1+ .pdf
VyNguyen709676
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
Sm321
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
sameer shah
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
nuttdpt
 
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docxDATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
SaffaIbrahim1
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
manishkhaire30
 
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
mkkikqvo
 
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Aggregage
 
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
Timothy Spann
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
Sachin Paul
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
aqzctr7x
 
一比一原版(harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(harvard毕业证书)哈佛大学毕业证如何办理一比一原版(harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(harvard毕业证书)哈佛大学毕业证如何办理
taqyea
 
The Ipsos - AI - Monitor 2024 Report.pdf
The  Ipsos - AI - Monitor 2024 Report.pdfThe  Ipsos - AI - Monitor 2024 Report.pdf
The Ipsos - AI - Monitor 2024 Report.pdf
Social Samosa
 
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
wyddcwye1
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
nuttdpt
 
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
nyfuhyz
 
University of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma TranscriptUniversity of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma Transcript
soxrziqu
 

Kürzlich hochgeladen (20)

A presentation that explain the Power BI Licensing
A presentation that explain the Power BI LicensingA presentation that explain the Power BI Licensing
A presentation that explain the Power BI Licensing
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
 
Open Source Contributions to Postgres: The Basics POSETTE 2024
Open Source Contributions to Postgres: The Basics POSETTE 2024Open Source Contributions to Postgres: The Basics POSETTE 2024
Open Source Contributions to Postgres: The Basics POSETTE 2024
 
writing report business partner b1+ .pdf
writing report business partner b1+ .pdfwriting report business partner b1+ .pdf
writing report business partner b1+ .pdf
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
 
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docxDATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
 
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
 
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
 
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
 
一比一原版(harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(harvard毕业证书)哈佛大学毕业证如何办理一比一原版(harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(harvard毕业证书)哈佛大学毕业证如何办理
 
The Ipsos - AI - Monitor 2024 Report.pdf
The  Ipsos - AI - Monitor 2024 Report.pdfThe  Ipsos - AI - Monitor 2024 Report.pdf
The Ipsos - AI - Monitor 2024 Report.pdf
 
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
 
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
 
University of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma TranscriptUniversity of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma Transcript
 

Convolutional Neural Networks CNN

  • 1.
  • 2. DATA SCIENCE 2 C o n v o l u t i o n a l N e u r a l N e t w o r k Field of Artificial Intelligence Field of M achine Learning Bangladesh University of Professionals(BUP) Deep Learning
  • 3. 3 Bangladesh University of Professionals(BUP) C o n v o l u t i o n a l N e u r a l N e t w o r k Input Classification Feature Extraction Car Not Car Output Input Feature Extraction + Classification Car Not Car Output Deep Learning Machine Learning
  • 4. 4 Bangladesh University of Professionals(BUP) C o n v o l u t i o n a l N e u r a l N e t w o r k Neural Network As like as Human Neuron Network
  • 5. 5 Bangladesh University of Professionals(BUP) C o n v o l u t i o n a l N e u r a l N e t w o r k Neural Network Artificial Neural Network (ANN) Regression and Classification Convolutional Neural Network (CNN) Computer Vision Recurrent Neural Network (RNN) Time Series Analysis
  • 6. AN N 6 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) CN N RN N
  • 7. 7 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Application of CNN Convolutional Neural Networks CNNs have the potentials to revolutionize many industries and improve our daily life. CNN have a wide range of applications. Such as:  Object detection.  Face Recognition.  Medical Imaging.  Analyzing Documents.  Understanding Climate.  Grey Areas.  Advertising.  Self Driving Car.  Security Systems.
  • 8. C o n v o l u t i o n a l N e u r a l N e t w o r k 8 snow covered ground, a blue and a white jacket, a black and a gray jacket, two people standing on skis, woman wearing a blue jacket, a blue helmet, a blue helmet on the head, blue jeans on the girl, a man and a snow covered mountain, a ski lift, white snow on the ground, trees covered in snow, a tree with no leaves. Optical Character Recognition is designed to convert your handwriting into text. Bangladesh University of Professionals(BUP) Application s
  • 9. Bangladesh University of Professionals(BUP)
  • 10. 1 0 Bangladesh University of Professionals(BUP) C o n v o l u t i o n a l N e u r a l N e t w o r k Convolutional Neural Networks (CNN) learns multilevel features and classifier in a joint fashion and performs much better than traditional approaches for various image classification and segmentation problems. Introduction
  • 11. 11 Bangladesh University of Professionals(BUP) C o n v o l u t i o n a l N e u r a l N e t w o r k CNN – What do they learn?
  • 12. CNN - Components There are four main components in the CNN: 1. Convolutional 2. Non-Linearity 3. Pooling or Sub Sampling 4. Classification (Fully Connected Layer)​ 1 2 Bangladesh University of Professionals(BUP) C o n v o l u t i o n a l N e u r a l N e t w o r k
  • 13. 1 3 Bangladesh University of Professionals(BUP) C o n v o l u t i o n a l N e u r a l N e t w o r k Input An image is a matrix of pixel values. If we consider a RGB image, each pixel will have the combined values of R, G and B. If we consider a gray scale image, the value of each pixel in the matrix will range from 0 to 255. What we see!!! What Computer See!!!
  • 14. 1 4 Bangladesh University of Professionals(BUP) C o n v o l u t i o n a l N e u r a l N e t w o r k Convolutional The primary purpose of Convolutional in case of CNN is to extract features from the input image. 0 0 0 0 1 1 1 1 1 4 Filter / Kernel / Feature Detector Convolved Features / Activation Map / Feature Map Image 0 0 0 1 0 0 1 1 1 1 0 0 0 0 1 1 1X1 1X1 1X1 1X0 1X0 1X1 0X0 0X0 0X1
  • 15. 1 5 Bangladesh University of Professionals(BUP) C o n v o l u t i o n a l N e u r a l N e t w o r k Convolutional… Input Image
  • 16. • The size of the output volume is controlled by three parameters that we need to decide before the convolutional step is performed: 1 6 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Convolutional…  Depth: Depth corresponds to the number of filters we use for the convolutional operation.  Stride: Stride is the number of pixels by which we slide our filter matrix over the input matrix.  Zero-padding: Sometimes, it is convenient to pad the input matrix with zeros around the border, so that we can apply the filter to bordering elements of our input image matrix.  With zero-padding wide convolutional  Without zero-padding narrow convolutional
  • 17. 1 7 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Non-Linearity (ReLU) • Replaces all negative pixel values in the feature map by zero. • The purpose of ReLU is to introduce non-linearity in CNN, since most of the real world data would be non-linear. • Other non-linear functions such as tanh (-1,1) or sigmoid (0,1) can also be used instead of ReLU (0,input) 23 18 75 101 0 25 0 20 100 25 0 35 18 0 20 15 15 20 -10 35 25 18 -110 -15 -10 20 23 18 75 101 25 100 Transfer Function 0,0
  • 18. 1 8 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Pooling Reduces the dimensionality of each feature map but retains the most important information. Pooling can be different types: Max, Average, Sum etc. 4 1 2 4 3 2 5 5 1 4 9 7 2 3 1 8 8 9 7 2x2 region
  • 19. 1 9 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Story so far….. • Together these layers extract the useful features from the images. • The output from the convolutional and pooling layers represent high-level features of the input image. High-level features Feature extraction 2x2 Subsampling 5x5 Convolution 2x2 Subsampling 5x5 Convolution input 32x32 C1 feature maps 28x28 S1 feature maps 14x14 C2 feature maps 10x10
  • 20. 2 0 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Fully Connected Layer • A traditional Multi-layer Perceptron. • The term “Fully-Connected” implies that every neuron in the previous layer is connected to every neuron on the next layer. • Their activations can hence be computed with a matrix multiplication followed by a bias offset. • The purpose of the fully connected layer is to use the high level features for classifying the input image into various classes based on the training dataset.
  • 21. 2 1 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Fully Connected Layer
  • 22. 2 2 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Fully Connected Layer
  • 23. 2 3
  • 24. 2 4 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Overall CNN Architecture Feature extraction 2x2 Subsampling 5x5 Convolution 2x2 Subsampling 5x5 Convolution input 32x32 C1 feature maps 28x28 S1 feature maps 14x14 C2 feature maps 10x10 S2 feature maps 5x5 n1 n2 output Classification Fully Connected 0 1 8 9
  • 25. 2 5 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Putting it all together – Training using Backpropagation Step-3: Calculate the total error at the output layer (summation over all 4 classes). Step-2: The network takes a training Image as input, goes through the forward propagation step (convolutional, ReLU and pooling operations along with forward propagation in the fully connected layer) and find the output probabilities for each class. Step-1: We initialize all filters and parameters / weights with random values. • Let’s say the output probabilities for the boat image above are [0.2,0.4,0.1,0.3]. • Since weight are randomly assigned for the first training example, output probabilities are also random.
  • 26. 2 6 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Step-4: Use Backpropagation to calculate the gradients of the error with respect to all weights in the network and use gradient descent to update all filter values/weights and parameter values to minimize the output error. • The weights are adjusted in proportion to their contribution to the total error. • When the same image is input again, output probabilities might now be [0.1, 0.1, 0.7, 0.1], which is closer to the target vector [0, 0, 1, 0]. • This means that the network has learnt to classify this particular image correctly by adjusting its weights / filters such that the output error is reduced. • Parameters like number of filters, filter sizes, architecture of the network etc. have all been fixed before Step 1 and do not change during training process - only the values of the filter matrix and connection weights get updated. Step-5: Repeat steps 2-4 with all images in the training set.
  • 27. 2 7 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Types of CNN Architectures
  • 28. 2 8 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Year CNN Architecture Developed By 1998 LeNet Yann LeCun et al. 2012 AlexNet Alex Krizhevsky, Geoffrey Hinton and Ilya Sutskever 2013 ZFNet Matthew Zeiler and Rob Fergus 2014 GoogleNet Google 2014 VGGNet Simonyan and Zisserman 2015 ResNet Kaiming He 2017 DenseNet Gao Huang, Zhuang Liu, Laurens van der Maaten and Killian Q.Weinberger
  • 29. 2 9 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) GoogleNet
  • 30. 3 0 C o n v o l u t i o n a l N e u r a l N e t w o r k Bangladesh University of Professionals(BUP) Limitation CNNs also have some drawbacks that limit their performance and applicability. One of the main disadvantages of CNNs is that they require a large amount of labeled data to train effectively, which can be costly and time-consuming to obtain and annotate. Coordinate Frame Classification of Images with different Positions Illustrates the dismantled components of a face