Cnn

DATASTRUCTURESAND
ALGORITHMS
Cnn
INTRODUCTION
What is a Neural Network?
An artificial neural network learning algorithm, or neural
network, or just neural net
, is a computational learning system that uses a network of
functions to understand and translate a data input of one
form into a desired output, usually in another form. The
concept of the artificial neural network was inspired by
human biology and the way neurons of the human brain
function together to understand inputs from human senses.
Neural network
Introduction to CNN (convolutional neural network):
When it comes to Machine Learning, Artificial Neural
Networks perform really well. Artificial Neural Networks are
used in various classification task like image, audio, words.
Different types of Neural Networks are used for different
purposes, for example for predicting the sequence of words we
use Recurrent Neural Networks more precisely an LSTM,
similarly for image classification we use Convolution
Neural Network. In this blog, we are going to build basic
building block for CNN.
The term “convolutional” means mathematical function
derived by integration from two distinct functions. It includes
rolling different elements together into a coherent whole by
multiplying them. Convolution describes how the other
function influences the shape of one function. In other words,
it is all about the relations between elements and their
operation as a whole.
DEFINITION
CNN is a specialized kind of neural network for
processing data that has a known, grid-like topology,
such as time-series (1D grid) , image data (2D grid)
,etc.
CNN is a deep learning algorithm, it is used in
various fields like speech recognition, image retrieval
and face recognition.
Layers in CNN:
i. Input layer
ii. Hidden layer
iii. Output layer
Input Layers: It’s the layer in which we give input to our model. The
number of neurons in this layer is equal to total number of features in our
data (number of pixels incase of an image).
Hidden Layer: The input from Input layer is then feed into the hidden
layer. There can be many hidden layers depending upon our model and
data size. Each hidden layers can have different numbers of neurons
which are generally greater than the number of features. The output from
each layer is computed by matrix multiplication of output of the previous
layer with learnable weights of that layer and then by addition of learnable
biases followed by activation function which makes the network nonlinear.
Output Layer: The output from the hidden layer is then fed into a logistic
function like sigmoid or softmax which converts the output of each class
into probability score of each class.
Here’s the basic python code for a neural network
with random inputs and two hidden layers.
activation = lambda x: 1.0/(1.0 + np.exp(-x)) # sigmoid
function
input = np.random.randn(3, 1)
hidden_1 = activation(np.dot(W1, input) + b1)
hidden_2 = activation(np.dot(W2, hidden_1) + b2)
output = np.dot(W3, hidden_2) + b3
LAYERS
Typical CNN has an architecture consists of :
1) Convolution layer
2) Pooling layer
3) Connected layer.
Convolution layer:
•Extract the unique features from the input image.
•Preservers the spatial relationship between pixels
by learning image features using small squares of
input data.
•Detect small ,meaningful features such as edges
with kernels.
•(i.e., identifying elements of an object, the face of
certain man, etc.).
Cnn
Convolution layer
Example
Then goes Rectified Linear Unit layer (aka ReLu).
This layer is an extension of a convolutional layer.
The purpose of ReLu is to increase the non-linearity
of the image. It is the process of stripping an image
of excessive fat to provide a better feature extraction.
Pool Layer:
•Reduce dimensionality,
•In all cases, pooling helps to make the representation
become approximately invariant to small translations of
input.
•Local translation can be very useful property if we care
more about whether some feature is present than exactly
where it is.
Types of pooling:
i. Max (works better)
ii. Average
iii.Sum
Max pooling
Average pooling
SUM pooling
Connected layer
The connected layer is a standard feed-forward
neural network. It is a final straight line before the
finish line where all the things are already evident.
And it is only a matter of time when the results are
confirmed.
Cnn
STRUCTURE
Cnn
Applications of CNN
Some of the key applications of CNN are listed here –
•Decoding Facial Recognition
•Analyzing documents
•Historic and environmental collections
•Understanding climate
•Grey areas
•Advertising
Other Interesting Fields
CNNs are poised to be the future with their introduction into
driverless cars, robots that can mimic human behavior, aides
to human genome mapping projects, predicting earthquakes
and natural disasters, and maybe even self-diagnoses of
medical problems. So, you wouldn't even have to drive down
to a clinic or schedule an appointment with a doctor to
ensure your sneezing attack or high fever is just the simple
flu and not symptoms of some rare disease. One problem
that researchers are working on with CNNs is brain cancer
detection. The earlier detection of brain cancer can prove to
be a big step in saving more lives affected by this illness.
Thank you
1 de 31

Recomendados

Neural  Networks  Ver1Neural  Networks  Ver1
Neural Networks Ver1ncct
2.2K visualizações56 slides
Deep Learning Deep Learning
Deep Learning Roshan Chettri
1.3K visualizações19 slides
Convolutional neural networkConvolutional neural network
Convolutional neural networkItachi SK
223 visualizações22 slides
Deep learning Deep learning
Deep learning Rajgupta258
1.6K visualizações20 slides
Digit recognitionDigit recognition
Digit recognitionbtandale
4.3K visualizações12 slides

Mais conteúdo relacionado

Mais procurados(20)

 Image Compression Using Neural Network Image Compression Using Neural Network
Image Compression Using Neural Network
Omkar Lokhande2.9K visualizações
Convolution neural networksConvolution neural networks
Convolution neural networks
Fares Hasan131 visualizações
Project presentationProject presentation
Project presentation
Madhv Kushawah1.7K visualizações
CNNCNN
CNN
Ukjae Jeong362 visualizações
Deep learning (2)Deep learning (2)
Deep learning (2)
Muhanad Al-khalisy168 visualizações
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
Yogendra Tamang7.5K visualizações
Top 10 deep learning algorithms you should know inTop 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know in
AmanKumarSingh9777 visualizações
Convolutional neural networkConvolutional neural network
Convolutional neural network
Ferdous ahmed553 visualizações
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance   lec 13Dr. Syed Muhammad Ali Tirmizi - Special topics in finance   lec 13
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance lec 13
Dr. Muhammad Ali Tirmizi., Ph.D.37 visualizações
Deep Belief NetworksDeep Belief Networks
Deep Belief Networks
Hasan H Topcu4.9K visualizações
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance   lec 14Dr. Syed Muhammad Ali Tirmizi - Special topics in finance   lec 14
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance lec 14
Dr. Muhammad Ali Tirmizi., Ph.D.49 visualizações
Neural networksNeural networks
Neural networks
HarshitGupta367132 visualizações
Artificial nueral network slideshareArtificial nueral network slideshare
Artificial nueral network slideshare
Red Innovators1.2K visualizações
NEURAL NETWORKSNEURAL NETWORKS
NEURAL NETWORKS
ESCOM1.5K visualizações
Artificial Neural Network.pptxArtificial Neural Network.pptx
Artificial Neural Network.pptx
ASHUTOSHMISHRA720383282 visualizações

Similar a Cnn(20)

Neural NetworkNeural Network
Neural Network
Ashish Kumar86 visualizações
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
RADO790095 visualizações
Som paper1.docSom paper1.doc
Som paper1.doc
Abhi Mediratta392 visualizações
Speech Processing  with deep learningSpeech Processing  with deep learning
Speech Processing with deep learning
Mohamed Essam102 visualizações
BASIC CONCEPT OF DEEP LEARNING.pptxBASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptx
RiteshPandey18406725 visualizações
Mnist report pptMnist report ppt
Mnist report ppt
RaghunandanJairam422 visualizações
Artificial Neural networksArtificial Neural networks
Artificial Neural networks
Learnbay Datascience25 visualizações
Deep Neural Network DNN.docxDeep Neural Network DNN.docx
Deep Neural Network DNN.docx
jaffarbikat3 visualizações
let's dive to deep learninglet's dive to deep learning
let's dive to deep learning
Mohamed Essam76 visualizações
Mnist reportMnist report
Mnist report
RaghunandanJairam148 visualizações
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
Lukas Masuch57.5K visualizações
Deep Learning Training at IntelDeep Learning Training at Intel
Deep Learning Training at Intel
Atul Vaish190 visualizações
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
IJCSIS Research Publications98 visualizações
11_Saloni Malhotra_SummerTraining_PPT.pptx11_Saloni Malhotra_SummerTraining_PPT.pptx
11_Saloni Malhotra_SummerTraining_PPT.pptx
SaloniMalhotra2325 visualizações
Neural NetworksNeural Networks
Neural Networks
Ismail El Gayar4.9K visualizações

Mais de rimshailyas1

Lab 1Lab 1
Lab 1rimshailyas1
45 visualizações19 slides
Stack arrayStack array
Stack arrayrimshailyas1
59 visualizações16 slides
Culture of balochistanCulture of balochistan
Culture of balochistanrimshailyas1
50 visualizações9 slides
Block inline pseudo emelemtsBlock inline pseudo emelemts
Block inline pseudo emelemtsrimshailyas1
35 visualizações10 slides
3d images3d images
3d imagesrimshailyas1
22 visualizações10 slides

Mais de rimshailyas1(15)

Canteen management system DocumentationCanteen management system Documentation
Canteen management system Documentation
rimshailyas12.7K visualizações
Lab 1Lab 1
Lab 1
rimshailyas145 visualizações
Stack arrayStack array
Stack array
rimshailyas159 visualizações
Culture of balochistanCulture of balochistan
Culture of balochistan
rimshailyas150 visualizações
Block inline pseudo emelemtsBlock inline pseudo emelemts
Block inline pseudo emelemts
rimshailyas135 visualizações
3d images3d images
3d images
rimshailyas122 visualizações
3d images3d images
3d images
rimshailyas135 visualizações
Slideshow+review+viewSlideshow+review+view
Slideshow+review+view
rimshailyas186 visualizações
DVRMDVRM
DVRM
rimshailyas194 visualizações
Transitions  animationTransitions  animation
Transitions animation
rimshailyas1255 visualizações
Types of presentation+file+homeTypes of presentation+file+home
Types of presentation+file+home
rimshailyas169 visualizações
Insert + designInsert + design
Insert + design
rimshailyas1233 visualizações
Determinants of fpDeterminants of fp
Determinants of fp
rimshailyas11.1K visualizações
Determinants of fp in pakistanDeterminants of fp in pakistan
Determinants of fp in pakistan
rimshailyas16K visualizações
Nervous systemNervous system
Nervous system
rimshailyas1227 visualizações

Último(20)

Business Analyst Series 2023 -  Week 3 Session 5Business Analyst Series 2023 -  Week 3 Session 5
Business Analyst Series 2023 - Week 3 Session 5
DianaGray1042 visualizações
Green Leaf Consulting: Capabilities DeckGreen Leaf Consulting: Capabilities Deck
Green Leaf Consulting: Capabilities Deck
GreenLeafConsulting170 visualizações
TE Connectivity: Card Edge InterconnectsTE Connectivity: Card Edge Interconnects
TE Connectivity: Card Edge Interconnects
CXL Forum93 visualizações
The Research Portal of Catalonia: Growing more (information) & more (services)The Research Portal of Catalonia: Growing more (information) & more (services)
The Research Portal of Catalonia: Growing more (information) & more (services)
CSUC - Consorci de Serveis Universitaris de Catalunya51 visualizações
Spesifikasi Lengkap ASUS Vivobook Go 14Spesifikasi Lengkap ASUS Vivobook Go 14
Spesifikasi Lengkap ASUS Vivobook Go 14
Dot Semarang34 visualizações
METHOD AND SYSTEM FOR PREDICTING OPTIMAL LOAD FOR WHICH THE YIELD IS MAXIMUM ...METHOD AND SYSTEM FOR PREDICTING OPTIMAL LOAD FOR WHICH THE YIELD IS MAXIMUM ...
METHOD AND SYSTEM FOR PREDICTING OPTIMAL LOAD FOR WHICH THE YIELD IS MAXIMUM ...
Prity Khastgir IPR Strategic India Patent Attorney Amplify Innovation23 visualizações
Java Platform Approach 1.0 - Picnic MeetupJava Platform Approach 1.0 - Picnic Meetup
Java Platform Approach 1.0 - Picnic Meetup
Rick Ossendrijver23 visualizações
CXL at OCPCXL at OCP
CXL at OCP
CXL Forum183 visualizações

Cnn

  • 4. What is a Neural Network? An artificial neural network learning algorithm, or neural network, or just neural net , is a computational learning system that uses a network of functions to understand and translate a data input of one form into a desired output, usually in another form. The concept of the artificial neural network was inspired by human biology and the way neurons of the human brain function together to understand inputs from human senses. Neural network
  • 5. Introduction to CNN (convolutional neural network): When it comes to Machine Learning, Artificial Neural Networks perform really well. Artificial Neural Networks are used in various classification task like image, audio, words. Different types of Neural Networks are used for different purposes, for example for predicting the sequence of words we use Recurrent Neural Networks more precisely an LSTM, similarly for image classification we use Convolution Neural Network. In this blog, we are going to build basic building block for CNN.
  • 6. The term “convolutional” means mathematical function derived by integration from two distinct functions. It includes rolling different elements together into a coherent whole by multiplying them. Convolution describes how the other function influences the shape of one function. In other words, it is all about the relations between elements and their operation as a whole.
  • 8. CNN is a specialized kind of neural network for processing data that has a known, grid-like topology, such as time-series (1D grid) , image data (2D grid) ,etc. CNN is a deep learning algorithm, it is used in various fields like speech recognition, image retrieval and face recognition.
  • 9. Layers in CNN: i. Input layer ii. Hidden layer iii. Output layer
  • 10. Input Layers: It’s the layer in which we give input to our model. The number of neurons in this layer is equal to total number of features in our data (number of pixels incase of an image). Hidden Layer: The input from Input layer is then feed into the hidden layer. There can be many hidden layers depending upon our model and data size. Each hidden layers can have different numbers of neurons which are generally greater than the number of features. The output from each layer is computed by matrix multiplication of output of the previous layer with learnable weights of that layer and then by addition of learnable biases followed by activation function which makes the network nonlinear. Output Layer: The output from the hidden layer is then fed into a logistic function like sigmoid or softmax which converts the output of each class into probability score of each class.
  • 11. Here’s the basic python code for a neural network with random inputs and two hidden layers. activation = lambda x: 1.0/(1.0 + np.exp(-x)) # sigmoid function input = np.random.randn(3, 1) hidden_1 = activation(np.dot(W1, input) + b1) hidden_2 = activation(np.dot(W2, hidden_1) + b2) output = np.dot(W3, hidden_2) + b3
  • 13. Typical CNN has an architecture consists of : 1) Convolution layer 2) Pooling layer 3) Connected layer.
  • 14. Convolution layer: •Extract the unique features from the input image. •Preservers the spatial relationship between pixels by learning image features using small squares of input data. •Detect small ,meaningful features such as edges with kernels. •(i.e., identifying elements of an object, the face of certain man, etc.).
  • 17. Then goes Rectified Linear Unit layer (aka ReLu). This layer is an extension of a convolutional layer. The purpose of ReLu is to increase the non-linearity of the image. It is the process of stripping an image of excessive fat to provide a better feature extraction.
  • 18. Pool Layer: •Reduce dimensionality, •In all cases, pooling helps to make the representation become approximately invariant to small translations of input. •Local translation can be very useful property if we care more about whether some feature is present than exactly where it is.
  • 19. Types of pooling: i. Max (works better) ii. Average iii.Sum
  • 24. The connected layer is a standard feed-forward neural network. It is a final straight line before the finish line where all the things are already evident. And it is only a matter of time when the results are confirmed.
  • 29. Some of the key applications of CNN are listed here – •Decoding Facial Recognition •Analyzing documents •Historic and environmental collections •Understanding climate •Grey areas •Advertising
  • 30. Other Interesting Fields CNNs are poised to be the future with their introduction into driverless cars, robots that can mimic human behavior, aides to human genome mapping projects, predicting earthquakes and natural disasters, and maybe even self-diagnoses of medical problems. So, you wouldn't even have to drive down to a clinic or schedule an appointment with a doctor to ensure your sneezing attack or high fever is just the simple flu and not symptoms of some rare disease. One problem that researchers are working on with CNNs is brain cancer detection. The earlier detection of brain cancer can prove to be a big step in saving more lives affected by this illness.