1. NEURAL NETWORK AND FUZZY
LOGIC
SEM-5
ORIENTATION
ORGANIZED BY
DEPARTMENT OF ELECTRONICS ENGINEERING
(NBA ACCREDITED)
1
Anuradha Joshi
Assistant Professor
Department of Electronics
Engineering
2. NEURAL NETWORK AND FUZZY LOGIC
(NNFL)
2
Subject Code - ELDO501
•Course Pre-requisite
•1. Knowledge of linear algebra, multivariate calculus, and
probability theory
•2. Knowledge of a programming language (PYTHON/C/C
++/ MATLAB recommended)
3. NEURAL NETWORK AND FUZZY LOGIC
(NNFL)
• Course Objectives:
• To study basics of biological Neural Network.
• To understand the different types of Artificial Neural Networks.
• To identify the applications of ANN.
• To study fuzzy logic and fuzzy systems
3
4. COURSE GRADING SCHEME FOR TW
4
Sr.
No.
Activity Methods Tools Rubrics
1 Prerequisite test on Individual chapter Indirect Survey 0%
2 Briefing of the chapter (Trailer) Direct PPT 0%
3 Active involvement & participation
Flip Classroom/ Live
Course Delivery/
Offline interactive
sessions
Interactive
session
30%
(Attendance/ watch
list)
4 Course Delivery Assessment Tests (2 min, after major topics) Indirect Survey
5%
(For Active
participation)
5 Feedback after the completion of major topics Indirect Survey
5%
(For Active
participation)
6
Collaborative learning (Group composed of students from
each group): (i) Discussion in forum, (ii) Poster Presentation,
& (iii) Graduate Paper on Course topic
Direct
Observation &
focused group
10%
7 Assignment Direct Evaluation 15%
8 class Test using MS Forms Direct Evaluation 15%
9 Interactive Online lab Session Online/ Recorded
Interactive
session
10%
(Attendance/ watch
list)
10 Online test after the completion online lab (based on skills) Direct Evaluation 10%
6. SYLLABUS
MODULE 1
Introduction
Biological neurons, McCulloch -Pitts
neuron model, Types of activation
function, Network architectures,
Knowledge representation. Linear & non-
linear separable classes & Pattern classes.
Learning processes: Supervised learning,
Unsupervised learning and Reinforcement
learning
Learning processes: Supervised
learning, Unsupervised learning and
Reinforcement learning
MODULE 2
Supervised Learning Networks
Perception Networks – continuous &
discrete, Perceptron convergence
theorem, Adaline, Madaline, Method of
steepest descent and least mean square
algorithm.
Back Propagation Network.
Radial Basis Function Network.
MODULE 3
Unsupervised Learning Network
Fixed weights competitive
nets. Kohonen Self-organizing
Feature Maps, Learning Vector
Quantization.
Adaptive Resonance Theory – 1.
7. SYLLABUS
MODULE 4
Adaptive Resonance Theory – 1.
Introduction, Training algorithms
for Pattern Association
Auto-associative Memory
Network, Hetero-associative
Memory Network, Bidirectional
Associative Memory.
MODULE 5
Fuzzy Logic
Fuzzy Sets, Fuzzy Relations and
Tolerance and Equivalence
Fuzzification and Defuzzification
MODULE 6
Case studies on ANN
Handwritten Digit Recognition,
Process Identification, Expert
Systems for Low Back Pain
Diagnosis.
9. Aerospace
•Altitude control of spacecraft
•Satellite altitude control
•Flow and mixture regulation
in aircraft deicing vehicles
Automotive
• Trainable fuzzy systems for
idle speed control
• Shift scheduling method for
automatic transmission
• Intelligent highway systems
• Traffic control
• Improving efficiency of
automatic transmissions
Fuzzy Logic - Applications
10. Business :
• Decision-making
support systems
• Personnel evaluation in a
large company
• Defense
In defense:
• Underwater target
recognition
• Automatic target
recognition of thermal
infrared images
• Naval decision support
aids
• Control of a
hypervelocity interceptor
• Fuzzy set modeling of
NATO decision making
Electronics :
• Control of automatic
exposure in video
cameras
• Humidity in a clean
room
• Air conditioning systems
• Washing machine timing
11. Industrial Sector
•Cement kiln controls heat
exchanger control
•Activated sludge wastewater
treatment process control
•Water purification plant control
•Quantitative pattern analysis for
industrial quality assurance
•Control of constraint satisfaction
problems in structural design
•Control of water purification plants
Manufacturing
•Optimization of cheese production
•Optimization of milk production