SlideShare ist ein Scribd-Unternehmen logo
1 von 22
Downloaden Sie, um offline zu lesen
CHAPTER 01
ROSENBLATT’S PERCEPTRON
CSC445: Neural Networks
Prof. Dr. Mostafa Gadal-Haqq M. Mostafa
Computer Science Department
Faculty of Computer & Information Sciences
AIN SHAMS UNIVERSITY
(most of figures in this presentation are copyrighted to Pearson Education, Inc.)
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
 Introduction
 The Perceptron
 The Perceptron Convergence Theorem
 Computer Experiment
 The Batch Perceptron Algorithm
2
Rosenblatt’s Perceptron
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq 3
Introduction
 The Perceptron:
 the simplest form of a neural network.
 consists of a single neuron with adjustable synaptic
weights and bias.
 can be used to classify linearly Separable patterns;
patterns that lie on opposite sides of a hyperplane.
 is limited to perform pattern classification with only two
classes.
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
The Perceptron
 Linearly and nonlinearly separable classes.
Figure 1.4 (a) A pair of linearly separable patterns. (b) A pair of
non-linearly separable.
4
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
The Perceptron
 A nonlinear neuron that is consists of a linear
combiner followed by a hard limiter (e.g., signum
activation function)
 Weights are adapted using an error-correction rule.
Figure 1.3 Signal-flow graph of the perceptron.
5






01
01
)(
v
v
vy 



m
i
iixwv
0



m
i
ii bxwv
1
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
The Perceptron
 The decision boundary
 A hyperplane defined by
 For the perceptron to function
Properly, the two classes C1
And C2 must be linearly
Separable. Figure 1.2 Illustration of the hyperplane
(in this example, a straight line) as decision
boundary for a two-dimensional, two-class
pattern-classification problem.
6
0
1


m
i
ii bxw
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
The Perceptron Convergence Algorithm
 the fixed-increment convergence theorem for the
perceptron (Rosenblatt, 1962):
 Let the subsets of training vectors X1 and X2 be linearly
separable. Let the inputs presented to the perceptron originate
from these two subsets. The perceptron converges after
some noiterations, in the sense:
is a solution vector for no  nmax .
Proof is reading: Pages (82-83 of ch01, Haykin).
7
...)2()1()( 000  nnn www
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
The Perceptron Convergence Algorithm
 We derive the error-correction learning algorithm as follows:
We write the input signal, the weights, and the bias:
Then
The learning algorithms find a weight vector w such that:
8
 T
m nxnxnxn )(),...,()(,1)( 21x
  T
m nwnwnwnwn )(),...,(),(,)( 210w
       


m
i
T
ii nnnxnwnv
0
)( xw
C1orinput vecteveryfor0  xxw
T
C2orinput vecteveryfor0  xxw
T
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
The Perceptron Convergence Algorithm
The learning algorithms find a weight vector W such that:
9
C1orinput vecteveryfor0  xxw
T
C2orinput vecteveryfor0  xxw
T
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
The Perceptron Convergence Algorithm
 Given the subsets of training vectors X1 and X2 , then
the training problem is then to find a weight vector
W such that the previous two inequalities are
satisfied. This is achieved when updating the
weights as follows:
 The learning-rate parameter (n) is a positive
number which could be variable. For fixed , we
have fixed-increment learning rule.
 The algorithm converges if (n) is a positive value.
10
  C2x(n)and0)(if)()()()1(  nnnnnn
T
xwxww 
  C1x(n)and0)(if)()()()1(  nnnnnn
T
xwxww 
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
The Perceptron Convergence Algorithm
11
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
The Perceptron Convergence Algorithm
12
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
Perceptron and Bayes Classifier
 Bayes Classifier
Figure 1.6 Signal-flow graph
of Gaussian classifier.
13
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
Perceptron and Bayes Classifier
 Bayes Classifier
Figure 1.7 Two overlapping, one-dimensional Gaussian distributions.
14
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq 15
The Batch Perceptron Algorithm
 We define the perceptron cost function as
 where H is the set of samples x misclassified by a
perceptron using w as its weight vector
 the cost function J(w) is differentiable with respect to
the weight vector w. Thus, differentiating J(w) with
respect to yields the gradient vector
 In the method of steepest descent, the adjustment to the
weight vector w at each time step of the algorithm is
applied in a direction opposite to the gradient vector .
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq 16
The Batch Perceptron Algorithm
 Accordingly, the algorithm takes the form
 which embodies the batch perceptron algorithm for
computing the weight vector W.
 The algorithm is said to be of the “batch” kind
because at each time-step of the algorithm, a batch
of misclassified samples is used to compute the
adjustment
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq 17
Batch Learning
 Presentation of all the N examples in the training
sample constitute one epoch.
 The cost function of the learning is defined by the
average error energy Eav
 The weights are updated epoch-by-epoch
 Advantages:
 Accurate estimation of the gradient vector.
 Parallelization of the learning process.
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
Computer Experiment: Pattern Classification
18
Figure 1.8 The double-moon classification problem.
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
Computer Experiment: Pattern Classification
19
Figure 1.9 Perceptron with the double-moon set at distance d = 1.
ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq
Computer Experiment: Pattern Classification
20
Figure 1.10 Perceptron with the double-moon set at distance d = -4.
•Problems:
•1.1, 1.4, and 1.5
•Computer Experiment
•1.6
Homework 1
21
Model building Through
Regression
Next Time
22

Weitere ähnliche Inhalte

Was ist angesagt?

Was ist angesagt? (20)

Mc culloch pitts neuron
Mc culloch pitts neuronMc culloch pitts neuron
Mc culloch pitts neuron
 
03 Single layer Perception Classifier
03 Single layer Perception Classifier03 Single layer Perception Classifier
03 Single layer Perception Classifier
 
Neural Networks: Support Vector machines
Neural Networks: Support Vector machinesNeural Networks: Support Vector machines
Neural Networks: Support Vector machines
 
2.5 backpropagation
2.5 backpropagation2.5 backpropagation
2.5 backpropagation
 
Artificial Neural Networks - ANN
Artificial Neural Networks - ANNArtificial Neural Networks - ANN
Artificial Neural Networks - ANN
 
Lecture 9 Perceptron
Lecture 9 PerceptronLecture 9 Perceptron
Lecture 9 Perceptron
 
Classification using back propagation algorithm
Classification using back propagation algorithmClassification using back propagation algorithm
Classification using back propagation algorithm
 
Adaptive Resonance Theory
Adaptive Resonance TheoryAdaptive Resonance Theory
Adaptive Resonance Theory
 
Hopfield Networks
Hopfield NetworksHopfield Networks
Hopfield Networks
 
04 Multi-layer Feedforward Networks
04 Multi-layer Feedforward Networks04 Multi-layer Feedforward Networks
04 Multi-layer Feedforward Networks
 
backpropagation in neural networks
backpropagation in neural networksbackpropagation in neural networks
backpropagation in neural networks
 
Neural Networks: Least Mean Square (LSM) Algorithm
Neural Networks: Least Mean Square (LSM) AlgorithmNeural Networks: Least Mean Square (LSM) Algorithm
Neural Networks: Least Mean Square (LSM) Algorithm
 
Feed forward ,back propagation,gradient descent
Feed forward ,back propagation,gradient descentFeed forward ,back propagation,gradient descent
Feed forward ,back propagation,gradient descent
 
Artificial Neural Network Lecture 6- Associative Memories & Discrete Hopfield...
Artificial Neural Network Lecture 6- Associative Memories & Discrete Hopfield...Artificial Neural Network Lecture 6- Associative Memories & Discrete Hopfield...
Artificial Neural Network Lecture 6- Associative Memories & Discrete Hopfield...
 
Artifical Neural Network and its applications
Artifical Neural Network and its applicationsArtifical Neural Network and its applications
Artifical Neural Network and its applications
 
Neural Networks: Model Building Through Linear Regression
Neural Networks: Model Building Through Linear RegressionNeural Networks: Model Building Through Linear Regression
Neural Networks: Model Building Through Linear Regression
 
Anfis (1)
Anfis (1)Anfis (1)
Anfis (1)
 
Artificial Neural Network Lect4 : Single Layer Perceptron Classifiers
Artificial Neural Network Lect4 : Single Layer Perceptron ClassifiersArtificial Neural Network Lect4 : Single Layer Perceptron Classifiers
Artificial Neural Network Lect4 : Single Layer Perceptron Classifiers
 
Artificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rulesArtificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rules
 
Counter propagation Network
Counter propagation NetworkCounter propagation Network
Counter propagation Network
 

Ähnlich wie Neural Networks: Rosenblatt's Perceptron

lecture07.ppt
lecture07.pptlecture07.ppt
lecture07.ppt
butest
 
ANNs have been widely used in various domains for: Pattern recognition Funct...
ANNs have been widely used in various domains for: Pattern recognition  Funct...ANNs have been widely used in various domains for: Pattern recognition  Funct...
ANNs have been widely used in various domains for: Pattern recognition Funct...
vijaym148
 
SOFT COMPUTERING TECHNICS -Unit 1
SOFT COMPUTERING TECHNICS -Unit 1SOFT COMPUTERING TECHNICS -Unit 1
SOFT COMPUTERING TECHNICS -Unit 1
sravanthi computers
 
Neural Networks Ver1
Neural  Networks  Ver1Neural  Networks  Ver1
Neural Networks Ver1
ncct
 

Ähnlich wie Neural Networks: Rosenblatt's Perceptron (20)

Artificial Neural Networks 1
Artificial Neural Networks 1Artificial Neural Networks 1
Artificial Neural Networks 1
 
ML_Unit_2_Part_A
ML_Unit_2_Part_AML_Unit_2_Part_A
ML_Unit_2_Part_A
 
20120140503023
2012014050302320120140503023
20120140503023
 
Artificial neural networks (2)
Artificial neural networks (2)Artificial neural networks (2)
Artificial neural networks (2)
 
lecture07.ppt
lecture07.pptlecture07.ppt
lecture07.ppt
 
Adaptive equalization
Adaptive equalizationAdaptive equalization
Adaptive equalization
 
Artificial Neural Networks (ANNs) focusing on the perceptron Algorithm.pptx
Artificial Neural Networks (ANNs) focusing on the perceptron Algorithm.pptxArtificial Neural Networks (ANNs) focusing on the perceptron Algorithm.pptx
Artificial Neural Networks (ANNs) focusing on the perceptron Algorithm.pptx
 
Artificial neural networks
Artificial neural networks Artificial neural networks
Artificial neural networks
 
Artificial Neural Networks ppt.pptx for final sem cse
Artificial Neural Networks  ppt.pptx for final sem cseArtificial Neural Networks  ppt.pptx for final sem cse
Artificial Neural Networks ppt.pptx for final sem cse
 
PPT presentation.pptx
PPT presentation.pptxPPT presentation.pptx
PPT presentation.pptx
 
ANNs have been widely used in various domains for: Pattern recognition Funct...
ANNs have been widely used in various domains for: Pattern recognition  Funct...ANNs have been widely used in various domains for: Pattern recognition  Funct...
ANNs have been widely used in various domains for: Pattern recognition Funct...
 
ai7.ppt
ai7.pptai7.ppt
ai7.ppt
 
m3 (2).pdf
m3 (2).pdfm3 (2).pdf
m3 (2).pdf
 
SOFT COMPUTERING TECHNICS -Unit 1
SOFT COMPUTERING TECHNICS -Unit 1SOFT COMPUTERING TECHNICS -Unit 1
SOFT COMPUTERING TECHNICS -Unit 1
 
1.pptx
1.pptx1.pptx
1.pptx
 
ACUMENS ON NEURAL NET AKG 20 7 23.pptx
ACUMENS ON NEURAL NET AKG 20 7 23.pptxACUMENS ON NEURAL NET AKG 20 7 23.pptx
ACUMENS ON NEURAL NET AKG 20 7 23.pptx
 
Economic Load Dispatch (ELD), Economic Emission Dispatch (EED), Combined Econ...
Economic Load Dispatch (ELD), Economic Emission Dispatch (EED), Combined Econ...Economic Load Dispatch (ELD), Economic Emission Dispatch (EED), Combined Econ...
Economic Load Dispatch (ELD), Economic Emission Dispatch (EED), Combined Econ...
 
An Artificial Neuron Implemented on an Actual Quantum Processor
An Artificial Neuron Implemented on an Actual Quantum ProcessorAn Artificial Neuron Implemented on an Actual Quantum Processor
An Artificial Neuron Implemented on an Actual Quantum Processor
 
Neural Networks Ver1
Neural  Networks  Ver1Neural  Networks  Ver1
Neural Networks Ver1
 
Optimization of Number of Neurons in the Hidden Layer in Feed Forward Neural ...
Optimization of Number of Neurons in the Hidden Layer in Feed Forward Neural ...Optimization of Number of Neurons in the Hidden Layer in Feed Forward Neural ...
Optimization of Number of Neurons in the Hidden Layer in Feed Forward Neural ...
 

Mehr von Mostafa G. M. Mostafa

Mehr von Mostafa G. M. Mostafa (19)

Csc446: Pattern Recognition
Csc446: Pattern Recognition Csc446: Pattern Recognition
Csc446: Pattern Recognition
 
CSC446: Pattern Recognition (LN8)
CSC446: Pattern Recognition (LN8)CSC446: Pattern Recognition (LN8)
CSC446: Pattern Recognition (LN8)
 
CSC446: Pattern Recognition (LN7)
CSC446: Pattern Recognition (LN7)CSC446: Pattern Recognition (LN7)
CSC446: Pattern Recognition (LN7)
 
CSC446: Pattern Recognition (LN6)
CSC446: Pattern Recognition (LN6)CSC446: Pattern Recognition (LN6)
CSC446: Pattern Recognition (LN6)
 
CSC446: Pattern Recognition (LN5)
CSC446: Pattern Recognition (LN5)CSC446: Pattern Recognition (LN5)
CSC446: Pattern Recognition (LN5)
 
CSC446: Pattern Recognition (LN4)
CSC446: Pattern Recognition (LN4)CSC446: Pattern Recognition (LN4)
CSC446: Pattern Recognition (LN4)
 
CSC446: Pattern Recognition (LN3)
CSC446: Pattern Recognition (LN3)CSC446: Pattern Recognition (LN3)
CSC446: Pattern Recognition (LN3)
 
Csc446: Pattren Recognition (LN2)
Csc446: Pattren Recognition (LN2)Csc446: Pattren Recognition (LN2)
Csc446: Pattren Recognition (LN2)
 
Csc446: Pattren Recognition
Csc446: Pattren RecognitionCsc446: Pattren Recognition
Csc446: Pattren Recognition
 
Csc446: Pattren Recognition (LN1)
Csc446: Pattren Recognition (LN1)Csc446: Pattren Recognition (LN1)
Csc446: Pattren Recognition (LN1)
 
Digital Image Processing: Image Restoration
Digital Image Processing: Image RestorationDigital Image Processing: Image Restoration
Digital Image Processing: Image Restoration
 
Digital Image Processing: Image Segmentation
Digital Image Processing: Image SegmentationDigital Image Processing: Image Segmentation
Digital Image Processing: Image Segmentation
 
Digital Image Processing: Image Enhancement in the Spatial Domain
Digital Image Processing: Image Enhancement in the Spatial DomainDigital Image Processing: Image Enhancement in the Spatial Domain
Digital Image Processing: Image Enhancement in the Spatial Domain
 
Digital Image Processing: Image Enhancement in the Frequency Domain
Digital Image Processing: Image Enhancement in the Frequency DomainDigital Image Processing: Image Enhancement in the Frequency Domain
Digital Image Processing: Image Enhancement in the Frequency Domain
 
Digital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image FundamentalsDigital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image Fundamentals
 
Digital Image Processing: An Introduction
Digital Image Processing: An IntroductionDigital Image Processing: An Introduction
Digital Image Processing: An Introduction
 
Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)
 
Neural Networks: Self-Organizing Maps (SOM)
Neural Networks:  Self-Organizing Maps (SOM)Neural Networks:  Self-Organizing Maps (SOM)
Neural Networks: Self-Organizing Maps (SOM)
 
Neural Networks: Principal Component Analysis (PCA)
Neural Networks: Principal Component Analysis (PCA)Neural Networks: Principal Component Analysis (PCA)
Neural Networks: Principal Component Analysis (PCA)
 

Kürzlich hochgeladen

Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
kauryashika82
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
QucHHunhnh
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
ciinovamais
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
QucHHunhnh
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
heathfieldcps1
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
negromaestrong
 

Kürzlich hochgeladen (20)

microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across Sectors
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writing
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptx
 
PROCESS RECORDING FORMAT.docx
PROCESS      RECORDING        FORMAT.docxPROCESS      RECORDING        FORMAT.docx
PROCESS RECORDING FORMAT.docx
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docx
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 

Neural Networks: Rosenblatt's Perceptron

  • 1. CHAPTER 01 ROSENBLATT’S PERCEPTRON CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq M. Mostafa Computer Science Department Faculty of Computer & Information Sciences AIN SHAMS UNIVERSITY (most of figures in this presentation are copyrighted to Pearson Education, Inc.)
  • 2. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq  Introduction  The Perceptron  The Perceptron Convergence Theorem  Computer Experiment  The Batch Perceptron Algorithm 2 Rosenblatt’s Perceptron
  • 3. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq 3 Introduction  The Perceptron:  the simplest form of a neural network.  consists of a single neuron with adjustable synaptic weights and bias.  can be used to classify linearly Separable patterns; patterns that lie on opposite sides of a hyperplane.  is limited to perform pattern classification with only two classes.
  • 4. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq The Perceptron  Linearly and nonlinearly separable classes. Figure 1.4 (a) A pair of linearly separable patterns. (b) A pair of non-linearly separable. 4
  • 5. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq The Perceptron  A nonlinear neuron that is consists of a linear combiner followed by a hard limiter (e.g., signum activation function)  Weights are adapted using an error-correction rule. Figure 1.3 Signal-flow graph of the perceptron. 5       01 01 )( v v vy     m i iixwv 0    m i ii bxwv 1
  • 6. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq The Perceptron  The decision boundary  A hyperplane defined by  For the perceptron to function Properly, the two classes C1 And C2 must be linearly Separable. Figure 1.2 Illustration of the hyperplane (in this example, a straight line) as decision boundary for a two-dimensional, two-class pattern-classification problem. 6 0 1   m i ii bxw
  • 7. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq The Perceptron Convergence Algorithm  the fixed-increment convergence theorem for the perceptron (Rosenblatt, 1962):  Let the subsets of training vectors X1 and X2 be linearly separable. Let the inputs presented to the perceptron originate from these two subsets. The perceptron converges after some noiterations, in the sense: is a solution vector for no  nmax . Proof is reading: Pages (82-83 of ch01, Haykin). 7 ...)2()1()( 000  nnn www
  • 8. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq The Perceptron Convergence Algorithm  We derive the error-correction learning algorithm as follows: We write the input signal, the weights, and the bias: Then The learning algorithms find a weight vector w such that: 8  T m nxnxnxn )(),...,()(,1)( 21x   T m nwnwnwnwn )(),...,(),(,)( 210w           m i T ii nnnxnwnv 0 )( xw C1orinput vecteveryfor0  xxw T C2orinput vecteveryfor0  xxw T
  • 9. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq The Perceptron Convergence Algorithm The learning algorithms find a weight vector W such that: 9 C1orinput vecteveryfor0  xxw T C2orinput vecteveryfor0  xxw T
  • 10. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq The Perceptron Convergence Algorithm  Given the subsets of training vectors X1 and X2 , then the training problem is then to find a weight vector W such that the previous two inequalities are satisfied. This is achieved when updating the weights as follows:  The learning-rate parameter (n) is a positive number which could be variable. For fixed , we have fixed-increment learning rule.  The algorithm converges if (n) is a positive value. 10   C2x(n)and0)(if)()()()1(  nnnnnn T xwxww    C1x(n)and0)(if)()()()1(  nnnnnn T xwxww 
  • 11. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq The Perceptron Convergence Algorithm 11
  • 12. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq The Perceptron Convergence Algorithm 12
  • 13. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq Perceptron and Bayes Classifier  Bayes Classifier Figure 1.6 Signal-flow graph of Gaussian classifier. 13
  • 14. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq Perceptron and Bayes Classifier  Bayes Classifier Figure 1.7 Two overlapping, one-dimensional Gaussian distributions. 14
  • 15. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq 15 The Batch Perceptron Algorithm  We define the perceptron cost function as  where H is the set of samples x misclassified by a perceptron using w as its weight vector  the cost function J(w) is differentiable with respect to the weight vector w. Thus, differentiating J(w) with respect to yields the gradient vector  In the method of steepest descent, the adjustment to the weight vector w at each time step of the algorithm is applied in a direction opposite to the gradient vector .
  • 16. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq 16 The Batch Perceptron Algorithm  Accordingly, the algorithm takes the form  which embodies the batch perceptron algorithm for computing the weight vector W.  The algorithm is said to be of the “batch” kind because at each time-step of the algorithm, a batch of misclassified samples is used to compute the adjustment
  • 17. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq 17 Batch Learning  Presentation of all the N examples in the training sample constitute one epoch.  The cost function of the learning is defined by the average error energy Eav  The weights are updated epoch-by-epoch  Advantages:  Accurate estimation of the gradient vector.  Parallelization of the learning process.
  • 18. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq Computer Experiment: Pattern Classification 18 Figure 1.8 The double-moon classification problem.
  • 19. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq Computer Experiment: Pattern Classification 19 Figure 1.9 Perceptron with the double-moon set at distance d = 1.
  • 20. ASU-CSC445: Neural Networks Prof. Dr. Mostafa Gadal-Haqq Computer Experiment: Pattern Classification 20 Figure 1.10 Perceptron with the double-moon set at distance d = -4.
  • 21. •Problems: •1.1, 1.4, and 1.5 •Computer Experiment •1.6 Homework 1 21