GEETHANJALI COLLEGE OF ENGINEERING & TECHNOLOGY

CHEERYAL(V) KEESARA (M)RR. District.

COURSE FILE
Department of Electrical & Electronics Engineering

Year & Semesters to whom subject is offered III-EEE

Name of the Subject Neural Networks and Fuzzy logic

Name of the Faculty: G.Srikanth Designation: Assistant Professor Department: EEE

1.1 Introduction to the subject

This course introduces the basics of Neural Networks and essentials of Artificial Neural
Networks with Single Layer and Multilayer Feed Forward Networks. Also deals with
Associate Memories and introduces Fuzzy sets and Fuzzy Logic system components.
The Neural Network and Fuzzy Network system application to Electrical Engineering is
also presented. This subject is very important and useful for doing Project Work.

I.2.Objectives of the subject

This course introduces the basics of Neural Networks and essentials of Artificial Neural
Networks with Single Layer and Multilayer Feed Forward Networks. Also deals with Associate
Memories and introduces Fuzzy sets and Fuzzy Logic system components. The Neural Network
and Fuzzy Network system application to Electrical Engineering is also presented. This subject
is very important and useful for doing Project Work.

1.3. JNTU Syllabus with Additional Topics

S.n UNIT NO Topic Additional Topics

o
1 1 Introduction to Neural Networks

Introduction, Humans and Computers, Organization of the

Brain, Biological Neuron
Biological and Artificial Neuron Models, Hodgkin-Huxley
Neuron Model, Integrate-and-Fire Neuron Model, Spiking
Neuron Model
Characteristics of ANN, McCulloch-Pitts Model, Historical
Developments,

i
 Potential Applications of ANN.

2 2 Essentials of Artificial Neural Networks

Artificial Neuron Model, Operations of Artificial Neuron, Types

of Neuron Activation Function,
, ANN Architectures, Classification Taxonomy of ANN –
Connectivity, Neural Dynamics (Activation and Synaptic)
Learning Strategy (Supervised, Unsupervised,
Reinforcement), Learning Rules, Types of
Application

3 3 Single Layer Feed Forward Neural Networks

Introduction, Perceptron Models: Discrete, Continuous and
Multi-Category,
Training Algorithms: Discrete and Continuous Perceptron
Networks, Perceptron Convergence theorem
Limitations of the Perceptron Model, Applications.

4 4 Multilayer Feed forward Neural Networks

Credit Assignment Problem, Generalized Delta Rule
Derivation of Backpropagation (BP) Training, Summary of
Backpropagation Algorithm, Kolmogorov Theorem, Learning
Difficulties and Improvements.

5 5 Associative Memories
Paradigms of Associative Memory, Pattern Mathematics,
Hebbian Learning, General Concepts of Associative Memory
(Associative Matrix, Association Rules, Hamming Distance,
The Linear Associator, Matrix Memories, Content
Addressable Memory), Bidirectional Associative Memory
(BAM) Architecture
BAM Training Algorithms: Storage and Recall Algorithm,
BAM Energy Function, Proof of BAM Stability Theorem

Architecture of Hopfield Network: Discrete and Continuous

versions, Storage and Recall Algorithm, Stability Analysis,
Capacity of the Hopfield Network Summary and Discussion of
Instance/Memory Based Learning Algorithms, Applications.

6 6 Classical & Fuzzy Sets

Introduction to classical sets - properties, Operations and
relations
Fuzzy sets, Membership, Uncertainty, Operations,
properties, fuzzy relations, cardinalities, membership
functions.

7 7 Fuzzy Logic System Components

Fuzzification, Membership value assignment, development of
rule base and decision making system
Defuzzification to crisp sets, Defuzzification methods.

ii
 8 8 Applications

Neural network applications: Process identification, control,

fault diagnosis and load forecasting.

Fuzzy logic applications: Fuzzy logic control and Fuzzy

classification.

Practical applications of ANN

Develop a simple ANN in MatLab

I.4. Sources of Information

I.4.1. Text books:-

1. Neural Networks, Fuzzy logic, Genetic algorithms: synthesis and applications by Rajasekharan and Rai – PHI
Publication.

2. Introduction to Neural Networks using MATLAB 6.0 - S.N.Sivanandam, S.Sumathi, S.N.Deepa, TMH, 2006

I.4.2. Reference Text Books:-

1. Neural Networks – James A Freeman and Davis Skapura, Pearson Education, 2002.

2. Neural Networks – Simon Hakins , Pearson Education

3. Neural Engineering by C.Eliasmith and CH.Anderson, PHI

4. Neural Networks and Fuzzy Logic System by Bart Kosko, PHI Publications.

1.4.3. Websites:-

I.4.4. Journels:-

iii
 1.5. Unit wise Summary

S.L Unit No Total no Topics to be covered Reg/Add Teaching Rem

no of Periods itional aids used arks
LCD/OHP/B
B
1 1 Introduction, Humans and Computers, Organization of the Regular LCD/ BB
Brain, Biological Neuron
Biological and Artificial Neuron Models, Hodgkin-Huxley Neuron Regular LCD/ BB
Model, Integrate-and-Fire Neuron Model, Spiking Neuron Model
Characteristics of ANN, McCulloch-Pitts Model, Historical Regular LCD/ BB
Developments,
Potential Applications of ANN. Regular LCD/ BB
Tutorial-1 BB
2 2 Artificial Neuron Model, Operations of Artificial Neuron, Types Regular LCD/ BB
of Neuron Activation Function,
, ANN Architectures, Classification Taxonomy of ANN – Regular LCD/ BB
Connectivity, Neural Dynamics (Activation and Synaptic)
Learning Strategy (Supervised, Unsupervised, Regular LCD/ BB
Reinforcement), Learning Rules, Types of
Application

Tutorial-2 BB
Solve University Question Papers BB
Assignment Test-I

3 3 Single Layer Feed Forward Neural Networks Regular LCD/ BB

Introduction, Perceptron Models: Discrete, Continuous and Regular LCD/ BB
Multi-Category,
Training Algorithms: Discrete and Continuous Perceptron Regular LCD/ BB
Networks, Perceptron Convergence theorem
Limitations of the Perceptron Model, Applications. Regular LCD/ BB

Regular LCD/ BB
Tutorial-3 BB
4 4 Multilayer Feed forward Neural Networks Regular LCD/ BB
Credit Assignment Problem, Generalized Delta Rule Regular LCD/ BB
Derivation of Backpropagation (BP) Training, Summary of Regular LCD/ BB
Backpropagation Algorithm, Kolmogorov Theorem, Learning
Difficulties and Improvements.

Tutorial-4 BB
Solve University Question Papers BB
Assignment Test-II
Mid Test-I

5 5 Associative Memories Regular LCD/ BB

Paradigms of Associative Memory, Pattern Mathematics, Regular LCD/ BB
Hebbian Learning, General Concepts of Associative Memory
(Associative Matrix, Association Rules, Hamming Distance,
The Linear Associator, Matrix Memories, Content Addressable Regular LCD/ BB
Memory), Bidirectional Associative Memory (BAM) Architecture
BAM Training Algorithms: Storage and Recall Algorithm, BAM Regular LCD/ BB
Energy Function, Proof of BAM Stability Theorem
iv
 Architecture of Hopfield Network: Discrete and Continuous Regular LCD/ BB
versions, Storage and Recall Algorithm, Stability Analysis,
Capacity of the Hopfield Network Summary and Discussion of
Instance/Memory Based Learning Algorithms, Applications.

Tutorial-5

6 6 Classical & Fuzzy Sets Regular LCD/ BB

Introduction to classical sets - properties, Operations and Regular LCD/ BB
relations
Fuzzy sets, Membership, Uncertainty, Operations, properties, Regular LCD/ BB
fuzzy relations, cardinalities, membership functions.

Tutorial-6 BB
Solve University Question Papers BB
Assignment Test-III

7 7 Fuzzy Logic System Components Regular LCD/ BB

Fuzzification, Membership value assignment, development of Regular LCD/ BB
rule base and decision making system
Defuzzification to crisp sets, Defuzzification methods. Regular LCD/ BB

Tutorial-7 BB
8 8 Applications Regular LCD/ BB
Neural network applications: Process identification, control, Regular LCD/ BB
fault diagnosis and load forecasting.

Fuzzy logic applications: Fuzzy logic control and Fuzzy Regular LCD/ BB
classification.

Tutorial-8 BB
Solve University Question Papers BB
Assignment Test-IV
Mid Test-II

1.6 Micro Plan:-

S.L Unit No Total no Topics to be covered Reg/Add Teaching Rem

no of Periods itional aids used arks
LCD/OHP/B
B
1 1 Introduction, Humans and Computers, Organization of the Regular LCD/ BB
Brain, Biological Neuron
Biological and Artificial Neuron Models, Hodgkin-Huxley Neuron Regular LCD/ BB
Model, Integrate-and-Fire Neuron Model, Spiking Neuron Model
v
 Characteristics of ANN, McCulloch-Pitts Model, Historical Regular LCD/ BB
Developments,
Potential Applications of ANN. Regular LCD/ BB
Tutorial-1 BB
2 2 Artificial Neuron Model, Operations of Artificial Neuron, Types Regular LCD/ BB
of Neuron Activation Function,
, ANN Architectures, Classification Taxonomy of ANN – Regular LCD/ BB
Connectivity, Neural Dynamics (Activation and Synaptic)
Learning Strategy (Supervised, Unsupervised, Regular LCD/ BB
Reinforcement), Learning Rules, Types of
Application

Tutorial-2 BB
Solve University Question Papers BB
Assignment Test-I

3 3 Single Layer Feed Forward Neural Networks Regular LCD/ BB

Introduction, Perceptron Models: Discrete, Continuous and Regular LCD/ BB
Multi-Category,
Training Algorithms: Discrete and Continuous Perceptron Regular LCD/ BB
Networks, Perceptron Convergence theorem
Limitations of the Perceptron Model, Applications. Regular LCD/ BB

Regular LCD/ BB
Tutorial-3 BB
4 4 Multilayer Feed forward Neural Networks Regular LCD/ BB
Credit Assignment Problem, Generalized Delta Rule Regular LCD/ BB
Derivation of Backpropagation (BP) Training, Summary of Regular LCD/ BB
Backpropagation Algorithm, Kolmogorov Theorem, Learning
Difficulties and Improvements.

Tutorial-4 BB
Solve University Question Papers BB
Assignment Test-II
Mid Test-I

5 5 Associative Memories Regular LCD/ BB

Paradigms of Associative Memory, Pattern Mathematics, Regular LCD/ BB
Hebbian Learning, General Concepts of Associative Memory
(Associative Matrix, Association Rules, Hamming Distance,
The Linear Associator, Matrix Memories, Content Addressable Regular LCD/ BB
Memory), Bidirectional Associative Memory (BAM) Architecture
BAM Training Algorithms: Storage and Recall Algorithm, BAM Regular LCD/ BB
Energy Function, Proof of BAM Stability Theorem

Architecture of Hopfield Network: Discrete and Continuous Regular LCD/ BB

versions, Storage and Recall Algorithm, Stability Analysis,
Capacity of the Hopfield Network Summary and Discussion of
Instance/Memory Based Learning Algorithms, Applications.

Tutorial-5

6 6 Classical & Fuzzy Sets Regular LCD/ BB

vi
 Introduction to classical sets - properties, Operations and Regular LCD/ BB
relations
Fuzzy sets, Membership, Uncertainty, Operations, properties, Regular LCD/ BB
fuzzy relations, cardinalities, membership functions.

Tutorial-6 BB
Solve University Question Papers BB
Assignment Test-III

7 7 Fuzzy Logic System Components Regular LCD/ BB

Fuzzification, Membership value assignment, development of Regular LCD/ BB
rule base and decision making system
Defuzzification to crisp sets, Defuzzification methods. Regular LCD/ BB

Tutorial-7 BB
8 8 Applications Regular LCD/ BB
Neural network applications: Process identification, control, Regular LCD/ BB
fault diagnosis and load forecasting.

Fuzzy logic applications: Fuzzy logic control and Fuzzy Regular LCD/ BB
classification.

Tutorial-8 BB
Solve University Question Papers BB
Assignment Test-IV
Mid Test-II

1.7..Subject Contents

1.7. 1.Synopsis page for each period(62 pages)

1.7.2 Detailed Lecture notes containing:

1.ppts

2.ohp slides

3.subjective type questions(approximately 5 t0 8 in no)

4.objective type questions(approximately 20 to 30 in no)

5.Any simulations

1.8.Course Review ( By the concerned Faculty):

(I)Aims

(II) Sample check

vii
 (III) End of the course report by the concerned faculty

GUIDELINES:

Distribution of periods :

No. of classes required to cover JNTU syllalbus : 40

No. of classes required to cover Additional topics : 4

No. of classes required to cover Assignment tests (for every 2 units 1 test) : 4

No. of classes required to cover tutorials : 8

No. of classes required to cover Mid tests : 2

No of classes required to solve University : 4

Question papers -------

Total periods 62

viii