Neural networks introduction

آيةالله عبدالحكيم
آيةالله عبدالحكيمJunior Web Developer um Information Technology Institute (ITI)
Neural Networks Introduction
Contents

1.   Introduction
2.   Biological Neural network
3.   Artificial Neural Network
4.   Comparison
5.   Benefits
6.   Neuron model
7.   Multilayer Neural Network
8.   Learning.
9.   Conclusion
Introduction

 Neural Network is a mathematical
  model of what goes in our mind to
  perform particular task or function.
 It is implemented using electronic
  components or simulated software.
 It is a system with many elements
  connected together.
Biological Neural Network

 Soma: body of the cell that houses
  the nucleus, in which the neuron's
  main genetic information can be
  found
 Dendrites: receptive
zones that receive
messages
Biological Neural Network (Cont,)

 Synapses are elementary structural
  and functional units that mediate the
  interactions between neurons.
 Axon: transmission line
 that sends messages.
Artificial Neural Network

 An artificial neural network (ANN) is a
  system composed of many simple
  processing elements (Neurons)
  operating in parallel whose function is
  determined by network structure,
  connection strengths (Weights), and
  the processing performed at
  computing element or nodes.
Difference Between Human Behavior and
 Neural Network Behavior

Human Behavior                           Neural Network Behavior

remember certain things completely,      Once we create a neural network, we
partially depend on capacity for         train it to become expert in an area.
learning.
If we do not practice what we learned,   Once fully trained, a neural net will not
we start to forget.                      forget.
The first 10 processes may be            If the results are repeatable it will be
accurate, but later we may start to      accurate.
make mistakes in the process.
                                         Faster inprocessing data and
                                         information
Benefits
 Nonlinearity: Perform operations that linear
  programming can’t.
 Fault tolerance: When one element fail NN
  continue without reduce parallelism.
 Adaptivity: NN has a capability to adapt their
  synaptic weights to changes in the surrounding
  environment.
 Contextual information: Every neuron in the
  network is potentially affected by the global
  activity of all other neurons
Neuron Model
 Neuron is a simple processing unit.
 The sole purpose of a Neuron is to receive
  electrical signals, accumulate them and see
  further if they are strong enough to pass
  forward.
 Single neuron is useless. It is the complex
  connection between them (weights) which
  makes brains capable of thinking and having a
  sense of consciousness.
Neuron Model (Cont,)
 Neuron Consist of:
  Inputs (Synapses): input signal.
  Weights (Dendrites): determines the importance
  of incoming value.
  Output (Axon): output to other neuron or of NN.
Neuron Model (Cont,)
 Output: is calculated by inputs which are
  multiplied by weights, and then computed by a
  mathematical function which determines the
  activation of the neuron.
 Activation Function:
Neuron Model (Cont,)
 Example:
 Output when single perceptron (neuron) is used.

 input      output
 00         0
 01         1
 10         1
 11         1
 The dark blue dots
represents values of true
and the light blue dot
represents a value of
False.
Neuron Model (Cont,)
 Example:
 Output when 2 perceptron (neuron) is used.
Multilayer Neural Network
 This network is feed-forward, means the values are propagated in
   one direction only.
 Input layer: takes the inputs and forwards it to hidden layer
 Middle layer: Without this layer,
 network would not be capable of
solving complex problems.
 Output layer: This layer
consists of neurons which output
the result
 Weights: for every neuron there
Are weights that for every input
To it.
Learning
 updating network architecture and connection weights so
  that network can efficiently perform a task.
Basic Learning Procedure
 run an input pattern through the function
 calculate the error (desired value – actual value)
 update the weights according to learning rate and error
 move onto next pattern
Overfitting
Occure when NN memorize patterns and loose the ability
  of generalization. Problem is when to stop learning
Learning Paradigm
 Supervised The correct answer is provided for the
 network for every input pattern Weights are adjusted
 regarding the correct answer.
 Unsupervised Does not need the correct output the
 system itself recognize the correlation and organize
 patterns into categories accordingly.
 Hybrid A combination of supervised and unsupervised,
 Some of the weights are provided with correct output while
 the others are automatically corrected.
Conclusion
 Neural Network is a modeling for human brain
 Neuron is the basic unit of NN
 To adapt NN to perform operation we want, it has to be
  trained
 Most practical form of NN is the one that has multilayer
 Try to avoid overfitting
Neural networks introduction
1 von 18

Recomendados

Artificial Neural Network(Artificial intelligence) von
Artificial Neural Network(Artificial intelligence)Artificial Neural Network(Artificial intelligence)
Artificial Neural Network(Artificial intelligence)spartacus131211
1.1K views12 Folien
Artificial Neural Network von
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkMuhammad Ishaq
1.3K views10 Folien
Introduction Of Artificial neural network von
Introduction Of Artificial neural networkIntroduction Of Artificial neural network
Introduction Of Artificial neural networkNagarajan
18.4K views93 Folien
Artificial Neural Network von
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkPrakash K
2K views58 Folien
Artificial nueral network slideshare von
Artificial nueral network slideshareArtificial nueral network slideshare
Artificial nueral network slideshareRed Innovators
1.2K views7 Folien
Artifical Neural Network and its applications von
Artifical Neural Network and its applicationsArtifical Neural Network and its applications
Artifical Neural Network and its applicationsSangeeta Tiwari
1.6K views31 Folien

Más contenido relacionado

Was ist angesagt?

Lecture11 - neural networks von
Lecture11 - neural networksLecture11 - neural networks
Lecture11 - neural networksAlbert Orriols-Puig
7.2K views32 Folien
Artificial Neural Network von
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkManasa Mona
1.7K views12 Folien
Artificial Neural Network seminar presentation using ppt. von
Artificial Neural Network seminar presentation using ppt.Artificial Neural Network seminar presentation using ppt.
Artificial Neural Network seminar presentation using ppt.Mohd Faiz
5.7K views32 Folien
Perceptron (neural network) von
Perceptron (neural network)Perceptron (neural network)
Perceptron (neural network)EdutechLearners
21.7K views33 Folien
Neural networks von
Neural networksNeural networks
Neural networksRizwan Rizzu
2.2K views27 Folien
Artificial Neural Network Topology von
Artificial Neural Network TopologyArtificial Neural Network Topology
Artificial Neural Network TopologyHarshana Madusanka Jayamaha
12.8K views18 Folien

Was ist angesagt?(20)

Artificial Neural Network von Manasa Mona
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Manasa Mona1.7K views
Artificial Neural Network seminar presentation using ppt. von Mohd Faiz
Artificial Neural Network seminar presentation using ppt.Artificial Neural Network seminar presentation using ppt.
Artificial Neural Network seminar presentation using ppt.
Mohd Faiz5.7K views
Artificial Neural Networks Lect3: Neural Network Learning rules von Mohammed Bennamoun
Artificial Neural Networks Lect3: Neural Network Learning rulesArtificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rules
Mohammed Bennamoun17.8K views
Perceptron von Nagarajan
PerceptronPerceptron
Perceptron
Nagarajan29.5K views
Artificial Neural Network von Atul Krishna
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Atul Krishna1.3K views
backpropagation in neural networks von Akash Goel
backpropagation in neural networksbackpropagation in neural networks
backpropagation in neural networks
Akash Goel26K views
Intro to Neural Networks von Dean Wyatte
Intro to Neural NetworksIntro to Neural Networks
Intro to Neural Networks
Dean Wyatte1.6K views
Neural network final NWU 4.3 Graphics Course von Mohaiminur Rahman
Neural network final NWU 4.3 Graphics CourseNeural network final NWU 4.3 Graphics Course
Neural network final NWU 4.3 Graphics Course
Mohaiminur Rahman941 views
Artificial neural network for machine learning von grinu
Artificial neural network for machine learningArtificial neural network for machine learning
Artificial neural network for machine learning
grinu572 views

Destacado

Neural network & its applications von
Neural network & its applications Neural network & its applications
Neural network & its applications Ahmed_hashmi
195.3K views50 Folien
Introduction to Neural Networks - Perceptron von
Introduction to Neural Networks - PerceptronIntroduction to Neural Networks - Perceptron
Introduction to Neural Networks - PerceptronHannes Hapke
1K views23 Folien
Neural networks von
Neural networksNeural networks
Neural networksSlideshare
6.9K views25 Folien
Deep Learning - Convolutional Neural Networks von
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksChristian Perone
71.4K views86 Folien
Artificial neural network von
Artificial neural networkArtificial neural network
Artificial neural networkDEEPASHRI HK
186.7K views22 Folien
Feature selection for detection of peer to-peer botnet traffic von
Feature selection for detection of peer to-peer botnet trafficFeature selection for detection of peer to-peer botnet traffic
Feature selection for detection of peer to-peer botnet trafficPratik Narang
2.4K views22 Folien

Destacado(20)

Neural network & its applications von Ahmed_hashmi
Neural network & its applications Neural network & its applications
Neural network & its applications
Ahmed_hashmi195.3K views
Introduction to Neural Networks - Perceptron von Hannes Hapke
Introduction to Neural Networks - PerceptronIntroduction to Neural Networks - Perceptron
Introduction to Neural Networks - Perceptron
Hannes Hapke1K views
Neural networks von Slideshare
Neural networksNeural networks
Neural networks
Slideshare6.9K views
Deep Learning - Convolutional Neural Networks von Christian Perone
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
Christian Perone71.4K views
Artificial neural network von DEEPASHRI HK
Artificial neural networkArtificial neural network
Artificial neural network
DEEPASHRI HK186.7K views
Feature selection for detection of peer to-peer botnet traffic von Pratik Narang
Feature selection for detection of peer to-peer botnet trafficFeature selection for detection of peer to-peer botnet traffic
Feature selection for detection of peer to-peer botnet traffic
Pratik Narang2.4K views
Neuron Mc Culloch Pitts dan Hebb von Sherly Uda
Neuron Mc Culloch Pitts dan HebbNeuron Mc Culloch Pitts dan Hebb
Neuron Mc Culloch Pitts dan Hebb
Sherly Uda9.9K views
Introduction to Neural networks (under graduate course) Lecture 9 of 9 von Randa Elanwar
Introduction to Neural networks (under graduate course) Lecture 9 of 9Introduction to Neural networks (under graduate course) Lecture 9 of 9
Introduction to Neural networks (under graduate course) Lecture 9 of 9
Randa Elanwar1.6K views
Fundamental, An Introduction to Neural Networks von Nelson Piedra
Fundamental, An Introduction to Neural NetworksFundamental, An Introduction to Neural Networks
Fundamental, An Introduction to Neural Networks
Nelson Piedra5K views
Introduction to Neural networks (under graduate course) Lecture 2 of 9 von Randa Elanwar
Introduction to Neural networks (under graduate course) Lecture 2 of 9Introduction to Neural networks (under graduate course) Lecture 2 of 9
Introduction to Neural networks (under graduate course) Lecture 2 of 9
Randa Elanwar2.8K views
Introduction to Neural networks (under graduate course) Lecture 1 of 9 von Randa Elanwar
Introduction to Neural networks (under graduate course) Lecture 1 of 9Introduction to Neural networks (under graduate course) Lecture 1 of 9
Introduction to Neural networks (under graduate course) Lecture 1 of 9
Randa Elanwar2.4K views
An Introduction to Neural Networks and Machine Learning von Chris Nicholls
An Introduction to Neural Networks and Machine LearningAn Introduction to Neural Networks and Machine Learning
An Introduction to Neural Networks and Machine Learning
Chris Nicholls186 views
Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ... von COMPEGENCE
Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...
Compegence: Dr. Rajaram Kudli - An Introduction to Artificial Neural Network ...
COMPEGENCE1.8K views
Introduction to Neural Networks in Tensorflow von Nicholas McClure
Introduction to Neural Networks in TensorflowIntroduction to Neural Networks in Tensorflow
Introduction to Neural Networks in Tensorflow
Nicholas McClure5.3K views
Machine learning with scikitlearn von Pratap Dangeti
Machine learning with scikitlearnMachine learning with scikitlearn
Machine learning with scikitlearn
Pratap Dangeti3.9K views
An introduction to Machine Learning (and a little bit of Deep Learning) von Thomas da Silva Paula
An introduction to Machine Learning (and a little bit of Deep Learning)An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)
neural network von STUDENT
neural networkneural network
neural network
STUDENT116.3K views

Similar a Neural networks introduction

Neuralnetwork 101222074552-phpapp02 von
Neuralnetwork 101222074552-phpapp02Neuralnetwork 101222074552-phpapp02
Neuralnetwork 101222074552-phpapp02Deepu Gupta
1.3K views47 Folien
Soft Computing-173101 von
Soft Computing-173101Soft Computing-173101
Soft Computing-173101AMIT KUMAR
3.1K views19 Folien
Neural networks are parallel computing devices.docx.pdf von
Neural networks are parallel computing devices.docx.pdfNeural networks are parallel computing devices.docx.pdf
Neural networks are parallel computing devices.docx.pdfneelamsanjeevkumar
11 views28 Folien
Neural networks of artificial intelligence von
Neural networks of artificial  intelligenceNeural networks of artificial  intelligence
Neural networks of artificial intelligencealldesign
1.8K views16 Folien
Neural network von
Neural networkNeural network
Neural networkSanthosh Gowda
746 views26 Folien

Similar a Neural networks introduction(20)

Neuralnetwork 101222074552-phpapp02 von Deepu Gupta
Neuralnetwork 101222074552-phpapp02Neuralnetwork 101222074552-phpapp02
Neuralnetwork 101222074552-phpapp02
Deepu Gupta1.3K views
Soft Computing-173101 von AMIT KUMAR
Soft Computing-173101Soft Computing-173101
Soft Computing-173101
AMIT KUMAR3.1K views
Neural networks are parallel computing devices.docx.pdf von neelamsanjeevkumar
Neural networks are parallel computing devices.docx.pdfNeural networks are parallel computing devices.docx.pdf
Neural networks are parallel computing devices.docx.pdf
Neural networks of artificial intelligence von alldesign
Neural networks of artificial  intelligenceNeural networks of artificial  intelligence
Neural networks of artificial intelligence
alldesign1.8K views
Data Science - Part VIII - Artifical Neural Network von Derek Kane
Data Science - Part VIII -  Artifical Neural NetworkData Science - Part VIII -  Artifical Neural Network
Data Science - Part VIII - Artifical Neural Network
Derek Kane4.6K views
Artificial Neural Network report von Anjali Agrawal
Artificial Neural Network reportArtificial Neural Network report
Artificial Neural Network report
Anjali Agrawal12.7K views
Neural Network von Sayyed Z
Neural NetworkNeural Network
Neural Network
Sayyed Z442 views
lecture07.ppt von butest
lecture07.pptlecture07.ppt
lecture07.ppt
butest12.9K views
Artificial Neural Networks for NIU session 2016 17 von Prof. Neeta Awasthy
Artificial Neural Networks for NIU session 2016 17 Artificial Neural Networks for NIU session 2016 17
Artificial Neural Networks for NIU session 2016 17
Introduction to Artificial Neural Networks von MuhammadMir92
Introduction to Artificial Neural Networks Introduction to Artificial Neural Networks
Introduction to Artificial Neural Networks
MuhammadMir9245 views
Artificial neural-network-paper-presentation-100115092527-phpapp02 von anandECE2010
Artificial neural-network-paper-presentation-100115092527-phpapp02Artificial neural-network-paper-presentation-100115092527-phpapp02
Artificial neural-network-paper-presentation-100115092527-phpapp02
anandECE201080 views
Artificial Neural Network Paper Presentation von guestac67362
Artificial Neural Network Paper PresentationArtificial Neural Network Paper Presentation
Artificial Neural Network Paper Presentation
guestac673626.8K views

Último

Kyo - Functional Scala 2023.pdf von
Kyo - Functional Scala 2023.pdfKyo - Functional Scala 2023.pdf
Kyo - Functional Scala 2023.pdfFlavio W. Brasil
449 views92 Folien
"Surviving highload with Node.js", Andrii Shumada von
"Surviving highload with Node.js", Andrii Shumada "Surviving highload with Node.js", Andrii Shumada
"Surviving highload with Node.js", Andrii Shumada Fwdays
53 views29 Folien
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue von
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlueMigrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlueShapeBlue
176 views20 Folien
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue von
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlueCloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlueShapeBlue
94 views13 Folien
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha... von
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...ShapeBlue
138 views18 Folien
The Power of Heat Decarbonisation Plans in the Built Environment von
The Power of Heat Decarbonisation Plans in the Built EnvironmentThe Power of Heat Decarbonisation Plans in the Built Environment
The Power of Heat Decarbonisation Plans in the Built EnvironmentIES VE
69 views20 Folien

Último(20)

"Surviving highload with Node.js", Andrii Shumada von Fwdays
"Surviving highload with Node.js", Andrii Shumada "Surviving highload with Node.js", Andrii Shumada
"Surviving highload with Node.js", Andrii Shumada
Fwdays53 views
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue von ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlueMigrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
ShapeBlue176 views
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue von ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlueCloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
ShapeBlue94 views
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha... von 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...
ShapeBlue138 views
The Power of Heat Decarbonisation Plans in the Built Environment von IES VE
The Power of Heat Decarbonisation Plans in the Built EnvironmentThe Power of Heat Decarbonisation Plans in the Built Environment
The Power of Heat Decarbonisation Plans in the Built Environment
IES VE69 views
Hypervisor Agnostic DRS in CloudStack - Brief overview & demo - Vishesh Jinda... von 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...
ShapeBlue120 views
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas... von Bernd Ruecker
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
Bernd Ruecker50 views
Igniting Next Level Productivity with AI-Infused Data Integration Workflows von Safe Software
Igniting Next Level Productivity with AI-Infused Data Integration Workflows Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Safe Software385 views
Backup and Disaster Recovery with CloudStack and StorPool - Workshop - Venko ... von ShapeBlue
Backup and Disaster Recovery with CloudStack and StorPool - Workshop - Venko ...Backup and Disaster Recovery with CloudStack and StorPool - Workshop - Venko ...
Backup and Disaster Recovery with CloudStack and StorPool - Workshop - Venko ...
ShapeBlue144 views
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti... von 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...
ShapeBlue98 views
The Role of Patterns in the Era of Large Language Models von Yunyao Li
The Role of Patterns in the Era of Large Language ModelsThe Role of Patterns in the Era of Large Language Models
The Role of Patterns in the Era of Large Language Models
Yunyao Li80 views
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N... von James Anderson
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N...
James Anderson156 views
NTGapps NTG LowCode Platform von Mustafa Kuğu
NTGapps NTG LowCode Platform NTGapps NTG LowCode Platform
NTGapps NTG LowCode Platform
Mustafa Kuğu365 views
Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ... von ShapeBlue
Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ...Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ...
Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ...
ShapeBlue79 views
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue von ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
ShapeBlue103 views
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT von 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
ShapeBlue166 views
Future of AR - Facebook Presentation von Rob McCarty
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook Presentation
Rob McCarty62 views

Neural networks introduction

  • 2. Contents 1. Introduction 2. Biological Neural network 3. Artificial Neural Network 4. Comparison 5. Benefits 6. Neuron model 7. Multilayer Neural Network 8. Learning. 9. Conclusion
  • 3. Introduction  Neural Network is a mathematical model of what goes in our mind to perform particular task or function.  It is implemented using electronic components or simulated software.  It is a system with many elements connected together.
  • 4. Biological Neural Network  Soma: body of the cell that houses the nucleus, in which the neuron's main genetic information can be found  Dendrites: receptive zones that receive messages
  • 5. Biological Neural Network (Cont,)  Synapses are elementary structural and functional units that mediate the interactions between neurons.  Axon: transmission line that sends messages.
  • 6. Artificial Neural Network  An artificial neural network (ANN) is a system composed of many simple processing elements (Neurons) operating in parallel whose function is determined by network structure, connection strengths (Weights), and the processing performed at computing element or nodes.
  • 7. Difference Between Human Behavior and Neural Network Behavior Human Behavior Neural Network Behavior remember certain things completely, Once we create a neural network, we partially depend on capacity for train it to become expert in an area. learning. If we do not practice what we learned, Once fully trained, a neural net will not we start to forget. forget. The first 10 processes may be If the results are repeatable it will be accurate, but later we may start to accurate. make mistakes in the process. Faster inprocessing data and information
  • 8. Benefits  Nonlinearity: Perform operations that linear programming can’t.  Fault tolerance: When one element fail NN continue without reduce parallelism.  Adaptivity: NN has a capability to adapt their synaptic weights to changes in the surrounding environment.  Contextual information: Every neuron in the network is potentially affected by the global activity of all other neurons
  • 9. Neuron Model  Neuron is a simple processing unit.  The sole purpose of a Neuron is to receive electrical signals, accumulate them and see further if they are strong enough to pass forward.  Single neuron is useless. It is the complex connection between them (weights) which makes brains capable of thinking and having a sense of consciousness.
  • 10. Neuron Model (Cont,)  Neuron Consist of: Inputs (Synapses): input signal. Weights (Dendrites): determines the importance of incoming value. Output (Axon): output to other neuron or of NN.
  • 11. Neuron Model (Cont,)  Output: is calculated by inputs which are multiplied by weights, and then computed by a mathematical function which determines the activation of the neuron.  Activation Function:
  • 12. Neuron Model (Cont,)  Example:  Output when single perceptron (neuron) is used. input output 00 0 01 1 10 1 11 1  The dark blue dots represents values of true and the light blue dot represents a value of False.
  • 13. Neuron Model (Cont,)  Example:  Output when 2 perceptron (neuron) is used.
  • 14. Multilayer Neural Network  This network is feed-forward, means the values are propagated in one direction only.  Input layer: takes the inputs and forwards it to hidden layer  Middle layer: Without this layer, network would not be capable of solving complex problems.  Output layer: This layer consists of neurons which output the result  Weights: for every neuron there Are weights that for every input To it.
  • 15. Learning  updating network architecture and connection weights so that network can efficiently perform a task. Basic Learning Procedure  run an input pattern through the function  calculate the error (desired value – actual value)  update the weights according to learning rate and error  move onto next pattern Overfitting Occure when NN memorize patterns and loose the ability of generalization. Problem is when to stop learning
  • 16. Learning Paradigm Supervised The correct answer is provided for the network for every input pattern Weights are adjusted regarding the correct answer. Unsupervised Does not need the correct output the system itself recognize the correlation and organize patterns into categories accordingly. Hybrid A combination of supervised and unsupervised, Some of the weights are provided with correct output while the others are automatically corrected.
  • 17. Conclusion  Neural Network is a modeling for human brain  Neuron is the basic unit of NN  To adapt NN to perform operation we want, it has to be trained  Most practical form of NN is the one that has multilayer  Try to avoid overfitting