Professional Documents
Culture Documents
Siddhartha: Course File Contents
Siddhartha: Course File Contents
Siddhartha: Course File Contents
PRINCIPAL
HOD/EEE
(ii). To demonstrate proficiency in the use of software and hardware which are
required to practice Electrical Engineering problems.
3.3. PROGRAM OUTCOMES (PO’s):
:2:
***
Faculty M Shankar
Text Books (to be acquired by the Students)
Neural Networks, Fuzzy logic, Genetic algorithms: synthesis and applications,
Book 1 Rajasekharan and Pal, PHI.
Neural Networks and Fuzzy Logic, C. Naga Bhaskar, G. Vijay Kumar, BS Publicatior-is.
Book 2
Reference Books
Book 3 Artificial Neural Networks, B. Yegnanarayana, PHI.
No of
Chapters
Classes
Unit Topic
Book 1 Book 2 Book 3 Book 4 Book 5
Introduction to Neural
Networks
I 19
Essentials of Artificial Neural
Networks
Single Layer Feed Forward
Neural Networks
II 14
Multilayer Feed forward
Neural Networks
III Associative Memories-I 18
Classical & Fuzzy Sets
IV 06
Fuzzy Logic System
IV 06
Components
Contact classes for syllabus coverage 63
Lectures beyond syllabus 02
Special descriptive Tests 02
Tutorial classes 05
Remedial/NPTEL classes 03
Total number of classes 75
LUNCH BREAK
9:50 10:40 11:30 12:20
MON NNFL
TUE
WED
THU
FRI
SAT
Course Objectives:
To introduce the basics of Neural Networks and its architectures.
To introduce the Fuzzy sets and Fuzzy Logic system components
To deal with the applications of Neural Networks and Fuzzy systems
Course Outcomes: After completion of this course, the students are able
To understand artificial neural network models and their training algorithms
To understand the concept of fuzzy logic system components, fuzzification and
defuzzification
Apply the above concepts to real-world problems and applications.
UNIT – I
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, Potential Applications of ANN.
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.
UNIT – II
FeedForward Neural Networks: 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.
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.
UNIT - III
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.
UNIT – IV
Classical and Fuzzy Sets: Introduction to classical sets - properties, Operations and
relations; Fuzzy sets, Membership, Uncertainty, Operations, properties, fuzzy relations,
cardinalities, membership functions.
UNIT – V
Fuzzy Logic System: Fuzzification, Membership value assignment, development of rule
base and decision making system, Defuzzification to crisp sets, Defuzzification methods.
Text Books:
1. Rajasekharan and Pai, Neural Networks, Fuzzy logic, Genetic algorithms: synthesis
and applications– PHI Publication, 1st Edition, 1905
2. Satish Kumar, Neural Networks, TMH, 2004.
Reference Books:
1. “James A Freeman and Davis Skapura”, Neural Networks, Pearson Education, 2002.
2. “Simon Hakins”, Neural Networks, Pearson Education, 3rd Edition 2008.
3. C. Eliasmith and Ch. Anderson, Neural Engineering, PHI, 2004.
***
SIDDHARTHA INSTIUTE OF ENGINEERING & TECHNOLOGY
Vinobha Nagar, Ibrahimpatnam, Ranga Reddy Dist
Department of Electrical and Electronics Engineering
***
SIDDHARTHA INSTIUTE OF ENGINEERING & TECHNOLOGY
Vinobha Nagar, Ibrahimpatnam, Ranga Reddy Dist
Department of Electrical and Electronics Engineering
Associative
3 Paradigms of Associative Memory 1 34
Memories
Pattern Mathematics, Hebbian
2 36
Learning
General Concepts of Associative
1 37
Memory
Associative Matrix, Association Rules,
1 38
Hamming Distance
The Linear Associator, Matrix
Memories, Content Addressable 2 40
Memory
Bidirectional Associative Memory
1 41
(BAM) Architecture
BAM Training Algorithms 1 42
5 Fuzzy Logic
System Fuzzification 1 59
Components
Membership value assignment 1 60
development of rule base and decision
making system 1 61
Defuzzification methods 1 63
1 https://www.btechguru.com/engineering-videos--electrical-engineering...
2 https://www.youtube.com/watch?v=xbYgKoG4x2g
3 https://nptel.ac.in/courses/108104049/13
DELIVERY/INSTRUCTIONAL METHODOLOGIES:
ASSESSMENT METHODOLOGIES-DIRECT
☐ UNIV.
√ ASSIGNMENTS √ STUD. SEMINARS ☐ TESTS/MODEL EXAMS
EXAMINATION
√ STUD. LAB PRACTICES √ STUD. VIVA ☐ MINI/MAJOR PROJECTS ☐ CERTIFICATIONS
ASSESSMENT METHODOLOGIES-INDIRECT
√ ASSESSMENT OF COURSE OUTCOMES (BY FEEDBACK, ONCE) √ STUDENT FEEDBACK ON FACULTY (TWICE)
2017-18 95.45
2016-17 87.5
2015-16 91
120
100
80
APPEARED
60
PASSED
PASS PERCENTAGE
40
20
0
2015-2016 2016-2017 2017-2018
SIDDHARTHA INSTIUTE OF ENGINEERING & TECHNOLOGY
Vinobha Nagar, Ibrahimpatnam, Ranga Reddy Dist
Department of Electrical and Electronics Engineering
6. Question Bank
4. Write short notes on sigmoidal gain and Threshold value in back propagation algorithm?
With a suitable diagram, derive the weight update equations in back propagation Algorithm for a
5. multilayer feed forward neural network and explain the effect of Learning rate and momentum
terms in weight update equations?
Unit – III
Very Short Answer Questions
1. What is Hebbian learning?
2. Define the hamming distance?
3. Define Associative matrix?
4. Write the associate rules?
5. Write the Hetero-associative memory?
Short Answer Questions
1. Draw the block diagram of static associative memory?
2. Write about the address-addressable memory?
3. Write about the memory based learning?
4. Describe the memory based learning in detail?
5. Write in details about discrete Hopfield network?
Long Answer Question
1. Write short notes on Hetero-associative memory and auto-associative memory?
2. With a neat diagram explain discrete-time bidirectional associative memory?
Suggest and Write about activation model, learning method for solving non-linear Activation
3.
problems?
4. Describe in detail memory-based learning algorithms?
Draw and explain the architectural graph of a Hopfield network consisting of N=4 neurons?
5.
Unit - IV
Very Short Questions
1. Describe the architecture of BAM?
Unit - V
Very Short Answer Questions
1. What are feature of membership functions?
2. Describe the trapezoidal membership functions?
3. Write the properties of crisp relations?
4. Define defuzziffication?
5. Write about aggregation of fuzzy rules?
Short Answer Questions
1. State the major implicit assumptions in a fuzzy control systems design?
2. What are the rules based format used to represent the fuzzy information?
3. Write short notes on Decision making logic in fuzzy logic system?
Write short notes on the following
4. i. Fuzzy synthesis evaluation.
ii. Fuzzy ordering.
5. Write short notes on fuzzification interface?