Neural Networks

Ismail El Gayar
Ismail El GayarSiebel CRM Consultant at Etisalat Misr à Etisalat Misr
BY:
Eng.Ismail El-Gayar
Under Supervision Of
Prof.Dr. Sheren Youssef
Introduction
Understanding the Brain
Neural Networks as a
Paradigm for Parallel Processing
• The Perceptron Network
• Training a Perceptron
• Multilayer Perceptrons
• Backpropagation
Algorithm
Two-Class Discrimination
Multiclass Discrimination
Multiple Hidden Layers
• Training Procedures
Improving Convergence
Momentum
Adaptive Learning Rate
• Learning Time
Time Delay Neural Networks
Recurrent Networks
Massive parallelism
Brain computer as an
information or signal processing
system, is composed of a large
number of a simple processing
elements, called neurons. These
neurons are interconnected by
numerous direct links, which are
called connection, and cooperate
which other to perform a parallel
distributed processing (PDP) in
order to soft a desired
computation tasks.
Connectionism
Brain computer is a highly
interconnected neurons system in
such a way that the state of one
neuron affects the potential of the
large number of other neurons
which are connected according to
weights or strength. The key idea of
such principle is the functional
capacity of biological neural nets
determs mostly not so of a single
neuron but of its connections
Associative distributed memory
Storage of information in a brain
is supposed to be concentrated
in synaptic connections of brain
neural network, or more
precisely, in the pattern of these
connections and strengths
(weights) of the synaptic
connections.
A process of pattern
recognition and pattern
manipulation is based
on:
How our brain
manipulates with
patterns ?
Processing:-
3
Human brain
contains a
massively
interconnected
net of 1010
-1011
(10 billion)
neurons
The Biological Neuron:-
The schematic
model of a
biological neuron
Synapses
Dendrites
Soma
Axon
Dendrit
e from
other
Axon from
other
neuron
1. Soma or body cell - is a large, round central body in which almost all the logical functions of the neuron
are realized.
2. The axon (output), is a nerve fibre attached to the soma which can serve as a final output channel of the
neuron. An axon is usually highly branched.
3. The dendrites (inputs)- represent a highly branching tree of fibres. These long irregularly shaped nerve
fibres (processes) are attached to the soma.
4. Synapses are specialized contacts on a neuron which are the termination points for the axons from other
neurons.
Neural Networks
?
Brain-Like Computer
Brain-like computer –
is a mathematical model of humane-brain
principles of computations. This computer consists
of those elements which can be called the
biological neuron prototypes, which are
interconnected by direct links called connections
and which cooperate to perform parallel
distributed processing (PDP) in order to solve a
desired computational task.
Neurons and Neural Net
The new paradigm of computing
mathematics consists of the combination
of such artificial neurons into some
artificial neuron net.
Artificial Neural Network – Mathematical
Paradigms of Brain-Like Computer
Brain-like Computer
NN as an model of brain-
like Computer
 An artificial neural network (ANN) is a massively
parallel distributed processor that has a natural
propensity for storing experimental knowledge and
making it available for use. It means that:
Knowledge is acquired by the network through a
learning (training) process;
 The strength of the interconnections between neurons is
implemented by means of the synaptic weights used to
store the knowledge.
The learning process is a procedure of the adapting the
weights with a learning algorithm in order to capture the
knowledge. On more mathematically, the aim of the
learning process is to map a given relation between inputs
and output (outputs) of the network.
Brain
The human brain is still not well
understood and indeed its behavior is very
complex!
There are about 10 billion neurons in the
human cortex and 60 trillion synapses of
connections
The brain is a highly complex, nonlinear
and parallel computer (information-
processing system)
ANN as a Brain-Like Computer
7
8
Artificial
Intellect with
Neural
Networks
Intelligent
Control
Intelligent
Control
Technical
Diagnistics
Technical
Diagnistics
Intelligent
Data Analysis
and Signal
Processing
Intelligent
Data Analysis
and Signal
Processing
Advance
Robotics
Advance
Robotics
Machine
Vision
Machine
Vision
Image &
Pattern
Recognition
Image &
Pattern
Recognition
Intelligent
Security
Systems
Intelligent
Security
Systems
Intelligentl
Medicine
Devices
Intelligentl
Medicine
Devices
Intelligent
Expert
Systems
Intelligent
Expert
Systems
Applications of Artificial Neural Networks
8
Artificial Neural Networks
Perceptrons
Multiple input nodes
Single output node
Takes a weighted sum of the inputs, call this S
Unit function calculates the output for the network
Useful to study because
We can use perceptrons to build larger networks
Perceptrons have limited representational abilities
We will look at concepts they can’t learn later
1( ,..., )nf x x
0 1( , ,..., )nw w w
- unknown multi-factor decision rule
Learning process using a representative learning set
- a set of weighting vectors is the result
of the learning process
1
0 1 1
ˆ( ,..., )
( ... )
n
n n
f x x
P w w x w x
=
= + + +
- a partially defined function, which
is an approximation of the decision
rule function 11
Why neural network?
Artificial Neuron
f is a function to be earned
are the inputs
φ is the activation function
1x
nx
1( ,..., )nxf x.
.
.
φ(z)
0 1 1 ... n nz w w x w x= + + +
1,..., nx x
Z is the weighted sum
1 0 1 1( ,..., ) ( ... )n n nf x x F w w x w x= + + +
Perceptrons:-
Output:- using Hardlims function
Simple Example:
Categorising Vehicles
Input to function: pixel data from vehicle images
Output: numbers: 1 for a car; 2 for a bus; 3 for a tank
INPUT INPUT INPUT INPUT
OUTPUT = 3 OUTPUT = 2 OUTPUT = 1 OUTPUT=1
General Idea
1.1
2.7
3.0
-1.3
2.7
4.2
-0.8
7.1
2.1
-1.2
1.1
0.2
0.3
HIDDEN LAYERSINPUT LAYER
NUMBERSINPUT
NUMBERSOUTPUT
OUTPUT LAYER CATEGORY
VALUES PROPAGATE THROUGH THE NETWORK
Cat A
Cat B
Cat C
Choose Cat A
(largest output value)
Value calculated using
all the input unit values
Calculation Example:-
Categorisation of 2x2 pixel black & white images
Into “bright” and “dark”
Representation of this rule:
If it contains 2, 3 or 4 white pixels, it is “bright”
If it contains 0 or 1 white pixels, it is “dark”
Perceptron architecture:
Four input units, one for each pixel
One output unit: +1 for white, -1 for dark
Calculation Example:-
Example calculation: x1=-1, x2=1, x3=1, x4=-1
S = 0.25*(-1) + 0.25*(1) + 0.25*(1) + 0.25*(-1) = 0
0 > -0.1, so the output from the ANN is +1
So the image is categorised as “bright”
Unit Functions
Linear Functions
Simply output the weighted sum
Threshold Functions
Output low values
 Until the weighted sum gets over a threshold
 Then output high values
 Equivalent of “firing” of neurons
Step function:
Output +1 if S > Threshold T
Output –1 otherwise
Sigma function:
Similar to step function but differentiable
Step
Function
Sigma
Function
Learning In Perceptron
Learning Process of ANN
Learn from experience
Learning algorithms
Recognize pattern of
activities
Involves 3 tasks
Compute outputs
Compare outputs with
desired targets
Adjust the weights and
repeat the process
Compute
output
Is
Desired
Output
achieved
Stop
Adjust
Weight
yes
No
Training a Perceptron:-
η -> Learning Rate
T -> target output
O -> output
X -> input
Worked Example
Return to the “bright” and “dark” example
Use a learning rate of η = 0.1
Suppose we have set random weights:
Worked Example
Use this training example, E, to update weights:
Here, x1 = -1, x2 = 1, x3 = 1, x4 = -1 as before
Propagate this information through the network:
 S = (-0.5 * 1) + (0.7 * -1) + (-0.2 * +1) + (0.1 * +1) + (0.9 * -1) = -2.2
Hence the network outputs o(E) = -1
But this should have been “bright”=+1
So t(E) = +1
Calculating the Error Values
Δ0 = η(t(E)-o(E))x0
= 0.1 * (1 - (-1)) * (1) = 0.1 * (2) = 0.2
Δ1 = η(t(E)-o(E))x1
= 0.1 * (1 - (-1)) * (-1) = 0.1 * (-2) = -0.2
Δ2 = η(t(E)-o(E))x2
= 0.1 * (1 - (-1)) * (1) = 0.1 * (2) = 0.2
Δ3 = η(t(E)-o(E))x3
= 0.1 * (1 - (-1)) * (1) = 0.1 * (2) = 0.2
Δ4 = η(t(E)-o(E))x4
Calculating the New Weights
w’0 = -0.5 + Δ0 = -0.5 + 0.2 = -0.3
w’1 = 0.7 + Δ1 = 0.7 + -0.2 = 0.5
w’2 = -0.2 + Δ2 = -0.2 + 0.2 = 0
w’3= 0.1 + Δ3 = 0.1 + 0.2 = 0.3
w’4 = 0.9 + Δ4 = 0.9 - 0.2 = 0.7
New Look Perceptron
Calculate for the example, E, again:
 S = (-0.3 * 1) + (0.5 * -1) + (0 * +1) + (0.3 * +1) + (0.7 * -1) = -1.2
Still gets the wrong categorisation
But the value is closer to zero (from -2.2 to -1.2)
In a few epochs time, this example will be correctly categorised
Neural Networks
Neural Networks
Neural Networks
Neural Networks
Neural Networks
Neural Networks
is an alternative neural network architecture whose primary purpose
is to work on continuous data.
The advantage of this architecture is to adapt the network online
and hence helpful in many real time applications, like time series
prediction, online spell check, continuous speech recognition,etc.
The architecture has a continuous input that is delayed and sent as
an input to the neural network.
As an example, consider training a feed forward neural network
being trained for a time series prediction. The desired output of
the network is the present state of the time series and inputs to
the neural network are the delayed time series (past values).
Hence, the output of the neural network is the predicted next value
in the time series which is computed as the function of the past
values of the time series.
Time delay neural network (TDNN):-
Recurrent Neural Networks
TYPES OF ANN:-
feed-forward feedback
4.1 Feed-forward networks
Feed-forward ANNs allow signals to
travel one way only; from input to
output. There is no feedback (loops)
i.e. the output of any layer does not
affect that same layer. Feed-forward
ANNs tend to be straight forward
networks that associate inputs with
outputs. They are extensively used in
pattern recognition.
4.2 Feedback networks
Feedback networks can have signals
travelling in both directions by
introducing loops in the network.
Feedback networks are very powerful
and can get extremely complicated.
Feedback networks are dynamic;
Some Topologies of ANN:-
Fully-connected feed-forward Partially recurrent network
Fully recurrent network
Recurrent Neural Networks:-
recurrent neural network:-
is a class of neural
network where connections
between units form a
directed cycle. This
creates an internal state
of the network which
allows it to exhibit
dynamic temporal behavior
Partially recurrent network
Fully recurrent network
References:-
[1] Simon Colton - www.doc.ic.ac.uk/~sgc/teaching/v231/
[2] http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html
[3] http://www.willamette.edu/~gorr/classes/cs449/intro.html
[4] http://www.scribd.com/doc/12774663/Neural-Network-Presentation
[5] http://www.speech.sri.com/people/anand/771/html/node32.html
[6] http://en.wikipedia.org/wiki/Recurrent_neural_network
Neural Networks
1 sur 39

Recommandé

Neural network final NWU 4.3 Graphics Course par
Neural network final NWU 4.3 Graphics CourseNeural network final NWU 4.3 Graphics Course
Neural network final NWU 4.3 Graphics CourseMohaiminur Rahman
941 vues41 diapositives
Artifical Neural Network and its applications par
Artifical Neural Network and its applicationsArtifical Neural Network and its applications
Artifical Neural Network and its applicationsSangeeta Tiwari
1.6K vues31 diapositives
Neural Networks par
Neural NetworksNeural Networks
Neural NetworksNikitaRuhela
15.3K vues41 diapositives
Artificial neural network for machine learning par
Artificial neural network for machine learningArtificial neural network for machine learning
Artificial neural network for machine learninggrinu
572 vues7 diapositives
Introduction Of Artificial neural network par
Introduction Of Artificial neural networkIntroduction Of Artificial neural network
Introduction Of Artificial neural networkNagarajan
18.4K vues93 diapositives
Neural network par
Neural networkNeural network
Neural networkRamesh Giri
732 vues16 diapositives

Contenu connexe

Tendances

Neural networks introduction par
Neural networks introductionNeural networks introduction
Neural networks introductionآيةالله عبدالحكيم
4.1K vues18 diapositives
Artificial intelligence NEURAL NETWORKS par
Artificial intelligence NEURAL NETWORKSArtificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKSREHMAT ULLAH
37.2K vues21 diapositives
Artificial Intelligence: Artificial Neural Networks par
Artificial Intelligence: Artificial Neural NetworksArtificial Intelligence: Artificial Neural Networks
Artificial Intelligence: Artificial Neural NetworksThe Integral Worm
7.9K vues21 diapositives
Artificial neural network par
Artificial neural networkArtificial neural network
Artificial neural networkAkshanshAgarwal4
840 vues25 diapositives
Artificial Neural Network seminar presentation using ppt. par
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 vues32 diapositives
Artificial Neural Network par
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkAtul Krishna
1.3K vues79 diapositives

Tendances(20)

Artificial intelligence NEURAL NETWORKS par REHMAT ULLAH
Artificial intelligence NEURAL NETWORKSArtificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKS
REHMAT ULLAH37.2K vues
Artificial Intelligence: Artificial Neural Networks par The Integral Worm
Artificial Intelligence: Artificial Neural NetworksArtificial Intelligence: Artificial Neural Networks
Artificial Intelligence: Artificial Neural Networks
The Integral Worm7.9K vues
Artificial Neural Network seminar presentation using ppt. par 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 vues
Artificial Neural Network par Atul Krishna
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Atul Krishna1.3K vues
backpropagation in neural networks par Akash Goel
backpropagation in neural networksbackpropagation in neural networks
backpropagation in neural networks
Akash Goel26K vues
Machine Learning: Introduction to Neural Networks par Francesco Collova'
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural Networks
Francesco Collova'16.1K vues
Artificial Neural Networks - ANN par Mohamed Talaat
Artificial Neural Networks - ANNArtificial Neural Networks - ANN
Artificial Neural Networks - ANN
Mohamed Talaat10.5K vues
Artificial Neural Network par Prakash K
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Prakash K2K vues
Convolutional Neural Networks (CNN) par Gaurav Mittal
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)
Gaurav Mittal58.5K vues
Neural networks.ppt par SrinivashR3
Neural networks.pptNeural networks.ppt
Neural networks.ppt
SrinivashR313.2K vues
neural network par STUDENT
neural networkneural network
neural network
STUDENT116.2K vues
Deep Learning - Convolutional Neural Networks par Christian Perone
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
Christian Perone71.4K vues
Artificial Neural Network Paper Presentation par guestac67362
Artificial Neural Network Paper PresentationArtificial Neural Network Paper Presentation
Artificial Neural Network Paper Presentation
guestac673626.8K vues

En vedette

Artificial neural network par
Artificial neural networkArtificial neural network
Artificial neural networkDEEPASHRI HK
186.7K vues22 diapositives
Feature detection - Image Processing par
Feature detection - Image ProcessingFeature detection - Image Processing
Feature detection - Image ProcessingRitesh Kanjee
2.2K vues10 diapositives
Artificial Neural Networks applications in Computer Aided Diagnosis. System d... par
Artificial Neural Networks applications in Computer Aided Diagnosis. System d...Artificial Neural Networks applications in Computer Aided Diagnosis. System d...
Artificial Neural Networks applications in Computer Aided Diagnosis. System d...Technological Ecosystems for Enhancing Multiculturality
784 vues23 diapositives
Neural networks and deep learning par
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learningJörgen Sandig
7.9K vues24 diapositives
Perceptron par
PerceptronPerceptron
PerceptronNagarajan
29.5K vues49 diapositives
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS par
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSEr Kaushal
13.6K vues26 diapositives

En vedette(20)

Artificial neural network par DEEPASHRI HK
Artificial neural networkArtificial neural network
Artificial neural network
DEEPASHRI HK186.7K vues
Feature detection - Image Processing par Ritesh Kanjee
Feature detection - Image ProcessingFeature detection - Image Processing
Feature detection - Image Processing
Ritesh Kanjee2.2K vues
Neural networks and deep learning par Jörgen Sandig
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
Jörgen Sandig7.9K vues
Perceptron par Nagarajan
PerceptronPerceptron
Perceptron
Nagarajan29.5K vues
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS par Er Kaushal
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
Er Kaushal13.6K vues
Neural Networks par Eric Su
Neural Networks Neural Networks
Neural Networks
Eric Su2.6K vues
Final presentation engineering as a career version1.1 par Deepesh Divaakaran
Final presentation engineering as a career version1.1Final presentation engineering as a career version1.1
Final presentation engineering as a career version1.1
Deepesh Divaakaran7.8K vues
Introductory Psychology: Sensation & Perception (Vision) par Brian Piper
Introductory Psychology: Sensation & Perception (Vision)Introductory Psychology: Sensation & Perception (Vision)
Introductory Psychology: Sensation & Perception (Vision)
Brian Piper20.7K vues
Visual perception 1 par cece2012
Visual perception 1Visual perception 1
Visual perception 1
cece201226.5K vues
Information processing approach par aj9ajeet
Information processing approachInformation processing approach
Information processing approach
aj9ajeet25.1K vues
Neural networks... par Molly Chugh
Neural networks...Neural networks...
Neural networks...
Molly Chugh16.1K vues
Neural networks par Slideshare
Neural networksNeural networks
Neural networks
Slideshare6.9K vues

Similaire à Neural Networks

Neural Networks Ver1 par
Neural  Networks  Ver1Neural  Networks  Ver1
Neural Networks Ver1ncct
2.2K vues56 diapositives
Artificial Neural networks par
Artificial Neural networksArtificial Neural networks
Artificial Neural networksLearnbay Datascience
25 vues29 diapositives
Artificial neural networks par
Artificial neural networks Artificial neural networks
Artificial neural networks ShwethaShreeS
122 vues24 diapositives
ANN - UNIT 1.pptx par
ANN - UNIT 1.pptxANN - UNIT 1.pptx
ANN - UNIT 1.pptxSRM Institute of Science and Technology
2 vues97 diapositives
Neural Network par
Neural NetworkNeural Network
Neural NetworkAshish Kumar
86 vues16 diapositives
Neural network par
Neural networkNeural network
Neural networkSanthosh Gowda
746 vues26 diapositives

Similaire à Neural Networks(20)

Neural Networks Ver1 par ncct
Neural  Networks  Ver1Neural  Networks  Ver1
Neural Networks Ver1
ncct2.2K vues
Artificial neural networks par ShwethaShreeS
Artificial neural networks Artificial neural networks
Artificial neural networks
ShwethaShreeS122 vues
Neural networks and deep learning par RADO7900
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
RADO790095 vues
NeuralProcessingofGeneralPurposeApproximatePrograms par Mohid Nabil
NeuralProcessingofGeneralPurposeApproximateProgramsNeuralProcessingofGeneralPurposeApproximatePrograms
NeuralProcessingofGeneralPurposeApproximatePrograms
Mohid Nabil138 vues
Towards neuralprocessingofgeneralpurposeapproximateprograms par Paridha Saxena
Towards neuralprocessingofgeneralpurposeapproximateprogramsTowards neuralprocessingofgeneralpurposeapproximateprograms
Towards neuralprocessingofgeneralpurposeapproximateprograms
Paridha Saxena70 vues
Soft Computing-173101 par AMIT KUMAR
Soft Computing-173101Soft Computing-173101
Soft Computing-173101
AMIT KUMAR3.1K vues
Neural networks of artificial intelligence par alldesign
Neural networks of artificial  intelligenceNeural networks of artificial  intelligence
Neural networks of artificial intelligence
alldesign1.8K vues
Basics of Artificial Neural Network par Subham Preetam
Basics of Artificial Neural Network Basics of Artificial Neural Network
Basics of Artificial Neural Network
Subham Preetam66 vues
Neural network par Faireen
Neural network Neural network
Neural network
Faireen585 vues

Plus de Ismail El Gayar

What is ETL? par
What is ETL?What is ETL?
What is ETL?Ismail El Gayar
19.9K vues13 diapositives
Geographic Information System for Egyptian Railway System(GIS) par
Geographic Information System for Egyptian Railway System(GIS)Geographic Information System for Egyptian Railway System(GIS)
Geographic Information System for Egyptian Railway System(GIS)Ismail El Gayar
2.3K vues36 diapositives
System science documentation par
System science documentationSystem science documentation
System science documentationIsmail El Gayar
660 vues96 diapositives
Prolog & lisp par
Prolog & lispProlog & lisp
Prolog & lispIsmail El Gayar
16.5K vues24 diapositives
Parallel architecture &programming par
Parallel architecture &programmingParallel architecture &programming
Parallel architecture &programmingIsmail El Gayar
1.4K vues33 diapositives
Object oriented methodology & unified modeling language par
Object oriented methodology & unified modeling languageObject oriented methodology & unified modeling language
Object oriented methodology & unified modeling languageIsmail El Gayar
9.8K vues30 diapositives

Plus de Ismail El Gayar(6)

Geographic Information System for Egyptian Railway System(GIS) par Ismail El Gayar
Geographic Information System for Egyptian Railway System(GIS)Geographic Information System for Egyptian Railway System(GIS)
Geographic Information System for Egyptian Railway System(GIS)
Ismail El Gayar2.3K vues
Parallel architecture &programming par Ismail El Gayar
Parallel architecture &programmingParallel architecture &programming
Parallel architecture &programming
Ismail El Gayar1.4K vues
Object oriented methodology & unified modeling language par Ismail El Gayar
Object oriented methodology & unified modeling languageObject oriented methodology & unified modeling language
Object oriented methodology & unified modeling language
Ismail El Gayar9.8K vues

Dernier

Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive par
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLiveAutomating a World-Class Technology Conference; Behind the Scenes of CiscoLive
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLiveNetwork Automation Forum
49 vues35 diapositives
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas... par
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 Ruecker
50 vues69 diapositives
Uni Systems for Power Platform.pptx par
Uni Systems for Power Platform.pptxUni Systems for Power Platform.pptx
Uni Systems for Power Platform.pptxUni Systems S.M.S.A.
60 vues21 diapositives
DRBD Deep Dive - Philipp Reisner - LINBIT par
DRBD Deep Dive - Philipp Reisner - LINBITDRBD Deep Dive - Philipp Reisner - LINBIT
DRBD Deep Dive - Philipp Reisner - LINBITShapeBlue
110 vues21 diapositives
Digital Personal Data Protection (DPDP) Practical Approach For CISOs par
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 CISOsPriyanka Aash
103 vues59 diapositives
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ... par
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 ...ShapeBlue
97 vues28 diapositives

Dernier(20)

Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive par Network Automation Forum
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLiveAutomating a World-Class Technology Conference; Behind the Scenes of CiscoLive
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas... par 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 vues
DRBD Deep Dive - Philipp Reisner - LINBIT par ShapeBlue
DRBD Deep Dive - Philipp Reisner - LINBITDRBD Deep Dive - Philipp Reisner - LINBIT
DRBD Deep Dive - Philipp Reisner - LINBIT
ShapeBlue110 vues
Digital Personal Data Protection (DPDP) Practical Approach For CISOs par 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 Aash103 vues
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ... par 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 ...
ShapeBlue97 vues
State of the Union - Rohit Yadav - Apache CloudStack par ShapeBlue
State of the Union - Rohit Yadav - Apache CloudStackState of the Union - Rohit Yadav - Apache CloudStack
State of the Union - Rohit Yadav - Apache CloudStack
ShapeBlue218 vues
Backup and Disaster Recovery with CloudStack and StorPool - Workshop - Venko ... par 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 ...
ShapeBlue114 vues
Why and How CloudStack at weSystems - Stephan Bienek - weSystems par 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
ShapeBlue172 vues
The Role of Patterns in the Era of Large Language Models par 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 Li74 vues
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue par 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
ShapeBlue147 vues
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R... par ShapeBlue
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
ShapeBlue105 vues
Extending KVM Host HA for Non-NFS Storage - Alex Ivanov - StorPool par ShapeBlue
Extending KVM Host HA for Non-NFS Storage -  Alex Ivanov - StorPoolExtending KVM Host HA for Non-NFS Storage -  Alex Ivanov - StorPool
Extending KVM Host HA for Non-NFS Storage - Alex Ivanov - StorPool
ShapeBlue56 vues
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha... par 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...
ShapeBlue113 vues
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue par 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
ShapeBlue68 vues
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue par ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
2FA and OAuth2 in CloudStack - Andrija Panić - ShapeBlue
ShapeBlue75 vues
GDG Cloud Southlake 28 Brad Taylor and Shawn Augenstein Old Problems in the N... par 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 Anderson142 vues
Keynote Talk: Open Source is Not Dead - Charles Schulz - Vates par ShapeBlue
Keynote Talk: Open Source is Not Dead - Charles Schulz - VatesKeynote Talk: Open Source is Not Dead - Charles Schulz - Vates
Keynote Talk: Open Source is Not Dead - Charles Schulz - Vates
ShapeBlue178 vues

Neural Networks

  • 1. BY: Eng.Ismail El-Gayar Under Supervision Of Prof.Dr. Sheren Youssef
  • 2. Introduction Understanding the Brain Neural Networks as a Paradigm for Parallel Processing • The Perceptron Network • Training a Perceptron • Multilayer Perceptrons • Backpropagation Algorithm Two-Class Discrimination Multiclass Discrimination Multiple Hidden Layers • Training Procedures Improving Convergence Momentum Adaptive Learning Rate • Learning Time Time Delay Neural Networks Recurrent Networks
  • 3. Massive parallelism Brain computer as an information or signal processing system, is composed of a large number of a simple processing elements, called neurons. These neurons are interconnected by numerous direct links, which are called connection, and cooperate which other to perform a parallel distributed processing (PDP) in order to soft a desired computation tasks. Connectionism Brain computer is a highly interconnected neurons system in such a way that the state of one neuron affects the potential of the large number of other neurons which are connected according to weights or strength. The key idea of such principle is the functional capacity of biological neural nets determs mostly not so of a single neuron but of its connections Associative distributed memory Storage of information in a brain is supposed to be concentrated in synaptic connections of brain neural network, or more precisely, in the pattern of these connections and strengths (weights) of the synaptic connections. A process of pattern recognition and pattern manipulation is based on: How our brain manipulates with patterns ? Processing:- 3 Human brain contains a massively interconnected net of 1010 -1011 (10 billion) neurons
  • 4. The Biological Neuron:- The schematic model of a biological neuron Synapses Dendrites Soma Axon Dendrit e from other Axon from other neuron 1. Soma or body cell - is a large, round central body in which almost all the logical functions of the neuron are realized. 2. The axon (output), is a nerve fibre attached to the soma which can serve as a final output channel of the neuron. An axon is usually highly branched. 3. The dendrites (inputs)- represent a highly branching tree of fibres. These long irregularly shaped nerve fibres (processes) are attached to the soma. 4. Synapses are specialized contacts on a neuron which are the termination points for the axons from other neurons.
  • 6. ? Brain-Like Computer Brain-like computer – is a mathematical model of humane-brain principles of computations. This computer consists of those elements which can be called the biological neuron prototypes, which are interconnected by direct links called connections and which cooperate to perform parallel distributed processing (PDP) in order to solve a desired computational task. Neurons and Neural Net The new paradigm of computing mathematics consists of the combination of such artificial neurons into some artificial neuron net. Artificial Neural Network – Mathematical Paradigms of Brain-Like Computer Brain-like Computer
  • 7. NN as an model of brain- like Computer  An artificial neural network (ANN) is a massively parallel distributed processor that has a natural propensity for storing experimental knowledge and making it available for use. It means that: Knowledge is acquired by the network through a learning (training) process;  The strength of the interconnections between neurons is implemented by means of the synaptic weights used to store the knowledge. The learning process is a procedure of the adapting the weights with a learning algorithm in order to capture the knowledge. On more mathematically, the aim of the learning process is to map a given relation between inputs and output (outputs) of the network. Brain The human brain is still not well understood and indeed its behavior is very complex! There are about 10 billion neurons in the human cortex and 60 trillion synapses of connections The brain is a highly complex, nonlinear and parallel computer (information- processing system) ANN as a Brain-Like Computer 7
  • 8. 8 Artificial Intellect with Neural Networks Intelligent Control Intelligent Control Technical Diagnistics Technical Diagnistics Intelligent Data Analysis and Signal Processing Intelligent Data Analysis and Signal Processing Advance Robotics Advance Robotics Machine Vision Machine Vision Image & Pattern Recognition Image & Pattern Recognition Intelligent Security Systems Intelligent Security Systems Intelligentl Medicine Devices Intelligentl Medicine Devices Intelligent Expert Systems Intelligent Expert Systems Applications of Artificial Neural Networks 8
  • 10. Perceptrons Multiple input nodes Single output node Takes a weighted sum of the inputs, call this S Unit function calculates the output for the network Useful to study because We can use perceptrons to build larger networks Perceptrons have limited representational abilities We will look at concepts they can’t learn later
  • 11. 1( ,..., )nf x x 0 1( , ,..., )nw w w - unknown multi-factor decision rule Learning process using a representative learning set - a set of weighting vectors is the result of the learning process 1 0 1 1 ˆ( ,..., ) ( ... ) n n n f x x P w w x w x = = + + + - a partially defined function, which is an approximation of the decision rule function 11 Why neural network?
  • 12. Artificial Neuron f is a function to be earned are the inputs φ is the activation function 1x nx 1( ,..., )nxf x. . . φ(z) 0 1 1 ... n nz w w x w x= + + + 1,..., nx x Z is the weighted sum 1 0 1 1( ,..., ) ( ... )n n nf x x F w w x w x= + + +
  • 14. Simple Example: Categorising Vehicles Input to function: pixel data from vehicle images Output: numbers: 1 for a car; 2 for a bus; 3 for a tank INPUT INPUT INPUT INPUT OUTPUT = 3 OUTPUT = 2 OUTPUT = 1 OUTPUT=1
  • 15. General Idea 1.1 2.7 3.0 -1.3 2.7 4.2 -0.8 7.1 2.1 -1.2 1.1 0.2 0.3 HIDDEN LAYERSINPUT LAYER NUMBERSINPUT NUMBERSOUTPUT OUTPUT LAYER CATEGORY VALUES PROPAGATE THROUGH THE NETWORK Cat A Cat B Cat C Choose Cat A (largest output value) Value calculated using all the input unit values
  • 16. Calculation Example:- Categorisation of 2x2 pixel black & white images Into “bright” and “dark” Representation of this rule: If it contains 2, 3 or 4 white pixels, it is “bright” If it contains 0 or 1 white pixels, it is “dark” Perceptron architecture: Four input units, one for each pixel One output unit: +1 for white, -1 for dark
  • 17. Calculation Example:- Example calculation: x1=-1, x2=1, x3=1, x4=-1 S = 0.25*(-1) + 0.25*(1) + 0.25*(1) + 0.25*(-1) = 0 0 > -0.1, so the output from the ANN is +1 So the image is categorised as “bright”
  • 18. Unit Functions Linear Functions Simply output the weighted sum Threshold Functions Output low values  Until the weighted sum gets over a threshold  Then output high values  Equivalent of “firing” of neurons Step function: Output +1 if S > Threshold T Output –1 otherwise Sigma function: Similar to step function but differentiable Step Function Sigma Function
  • 20. Learning Process of ANN Learn from experience Learning algorithms Recognize pattern of activities Involves 3 tasks Compute outputs Compare outputs with desired targets Adjust the weights and repeat the process Compute output Is Desired Output achieved Stop Adjust Weight yes No
  • 21. Training a Perceptron:- η -> Learning Rate T -> target output O -> output X -> input
  • 22. Worked Example Return to the “bright” and “dark” example Use a learning rate of η = 0.1 Suppose we have set random weights:
  • 23. Worked Example Use this training example, E, to update weights: Here, x1 = -1, x2 = 1, x3 = 1, x4 = -1 as before Propagate this information through the network:  S = (-0.5 * 1) + (0.7 * -1) + (-0.2 * +1) + (0.1 * +1) + (0.9 * -1) = -2.2 Hence the network outputs o(E) = -1 But this should have been “bright”=+1 So t(E) = +1
  • 24. Calculating the Error Values Δ0 = η(t(E)-o(E))x0 = 0.1 * (1 - (-1)) * (1) = 0.1 * (2) = 0.2 Δ1 = η(t(E)-o(E))x1 = 0.1 * (1 - (-1)) * (-1) = 0.1 * (-2) = -0.2 Δ2 = η(t(E)-o(E))x2 = 0.1 * (1 - (-1)) * (1) = 0.1 * (2) = 0.2 Δ3 = η(t(E)-o(E))x3 = 0.1 * (1 - (-1)) * (1) = 0.1 * (2) = 0.2 Δ4 = η(t(E)-o(E))x4
  • 25. Calculating the New Weights w’0 = -0.5 + Δ0 = -0.5 + 0.2 = -0.3 w’1 = 0.7 + Δ1 = 0.7 + -0.2 = 0.5 w’2 = -0.2 + Δ2 = -0.2 + 0.2 = 0 w’3= 0.1 + Δ3 = 0.1 + 0.2 = 0.3 w’4 = 0.9 + Δ4 = 0.9 - 0.2 = 0.7
  • 26. New Look Perceptron Calculate for the example, E, again:  S = (-0.3 * 1) + (0.5 * -1) + (0 * +1) + (0.3 * +1) + (0.7 * -1) = -1.2 Still gets the wrong categorisation But the value is closer to zero (from -2.2 to -1.2) In a few epochs time, this example will be correctly categorised
  • 33. is an alternative neural network architecture whose primary purpose is to work on continuous data. The advantage of this architecture is to adapt the network online and hence helpful in many real time applications, like time series prediction, online spell check, continuous speech recognition,etc. The architecture has a continuous input that is delayed and sent as an input to the neural network. As an example, consider training a feed forward neural network being trained for a time series prediction. The desired output of the network is the present state of the time series and inputs to the neural network are the delayed time series (past values). Hence, the output of the neural network is the predicted next value in the time series which is computed as the function of the past values of the time series. Time delay neural network (TDNN):-
  • 35. TYPES OF ANN:- feed-forward feedback 4.1 Feed-forward networks Feed-forward ANNs allow signals to travel one way only; from input to output. There is no feedback (loops) i.e. the output of any layer does not affect that same layer. Feed-forward ANNs tend to be straight forward networks that associate inputs with outputs. They are extensively used in pattern recognition. 4.2 Feedback networks Feedback networks can have signals travelling in both directions by introducing loops in the network. Feedback networks are very powerful and can get extremely complicated. Feedback networks are dynamic;
  • 36. Some Topologies of ANN:- Fully-connected feed-forward Partially recurrent network Fully recurrent network
  • 37. Recurrent Neural Networks:- recurrent neural network:- is a class of neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior Partially recurrent network Fully recurrent network
  • 38. References:- [1] Simon Colton - www.doc.ic.ac.uk/~sgc/teaching/v231/ [2] http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html [3] http://www.willamette.edu/~gorr/classes/cs449/intro.html [4] http://www.scribd.com/doc/12774663/Neural-Network-Presentation [5] http://www.speech.sri.com/people/anand/771/html/node32.html [6] http://en.wikipedia.org/wiki/Recurrent_neural_network