SN 21CSF-335 Soft Computing L T P S C CH Course Type

1 3 0 0 0 3 45 Elective
Course Code(s)
PRE-REQUISITE Probability and Statistics
Basics of Python and Machine learning/AI 20CST-234
CO-REQUISITE NA
ANTI- NA
REQUISITE

a. COURSE DESCRIPTION
Soft Computing is the use of approximate calculations to provide imprecise but usable solutions to
complex computational problems. The approach enable solutions for problems that may be either
unsolvable or just too time- consuming to solve with current hardware.Soft computing is sometimes
referred to as computational intelligence. Soft computing provides an approach to problem-solving using
means other than computers. Wth the human mind as a role model, soft computing is tolerant of partial
truths, uncertainty, imprecision and approximation, unlike traditional computing models. The tolerance
of soft computing allows researchers to approach some problems that traditional computing can’t
process.

b. COURSE OBJECTIVES

The Course aims to:

1. To introduce soft computing concepts and techniques of artificial neural networks, fuzzy sets,
fuzzy logic and genetic algorithms.
2. To understand the various techniques from the application point of view.
3. To analyze various soft computing techniques and decide the technique to be used in a particular
problem situation.
4. To implement soft computing based solutions for real-world problems.

c. COURSE OUTCOMES
CO1 Identify and describe soft computing techniques and their roles in building 1
intelligent. Machines
CO2 Recognize the feasibility of applying a soft computing methodology for a 2,4
particular problem.
CO3 Apply fuzzy logic and reasoning to handle uncertainty and solve engineering 3
problems, genetic algorithms to combinatorial optimization problems and
neural networks to pattern classification and regression problems.
CO4 Effectively use modern software tools to solve real problems using a soft 3
 computing approach.

CO5 Evaluate various soft computing approaches for a given problem. 4

*Last Column describes the mapping with BT. The course will go to at max level 4.

d. SYLLABUS
Unit-1 Basic Structure Contact
Hours:15
Introduction to Soft Introduction to Soft Computing, Difference between soft and
Computing hard computing, Major Areas of Soft Computing, Applications of
Soft Computing,
Introduction to Neural Neural network and its working, architectures, learning rules for
Networks neural network, learning rules for neural network II
Neural Network Types Taxonomy of neural networks, fully connected layer , Back
Propagation.
Unit-2 Basics of Computing Contact
Hours:15
Advanced Neural
Loss functions and optimization, Cross entropy loss and
Network activation function.
Variations of Neural Convolution neural networks, object localization and detection
Networks
Variations of Neural Auto encoder, Variation auto encoder, RNN, GANs.
Networks-II
Unit-3 Advanced Theories Contact
Hours:15
Fuzzy Logic Fuzzy Set theory, Fuzzy versus Crisp set, Fuzzy Relation,
Fuzzification, Fuzzy Logic
Fuzzy Systems Fuzzy Rule based systems, Predicate logic, Fuzzy Decision
Making Fuzzy Control Systems, Fuzzy Classification., Minmax
Composition, Defuzzification Method.
Genetic Algorithms
History of Genetic Algorithms (GA), Fundamentals of Genetic
Algorithms, Encoding, Operators of Genetic Algorithm, Basic
 Genetic Algorithm.

e. TEXTBOOKS / REFERENCE BOOKS

TEXT BOOKS

T1.Timothy J. Ross, “Fuzzy Logic with Engineering Applications”.

T2.S.N.Sivanandam, S.N Deepa, “Principles of Soft Computing”

T3.Lofti Zadeh “Fuzzy Logic and Soft Computing” Word Scientific, 1995.

T4 Samir Roy,Udit Chakraborty, “Introduction to Soft Computing:Neuro-Fuzzy and Genetic

Algorithms”, Pearson.

REFERENCE BOOKS
R1 Bart Kosko, “Neural Network and Fuzzy Systems: A Dynamic System Approach to
Machine” Prentice-Hall 1998

R2 L. Fausett, “Fundamentals of Neural Networks: Architectures, Algorithms, and

Applications”, Prentice-Hall, 1994

R3 Jack M. Zurada, “Introduction to Artificial Neural Systems”, PWS Publishing Co., Boston,
2000.
R4 J S R Jang, “Neuro-Fuzzy & Soft Computing,”, Pearson.

f. ASSESSMENT PATTERN - INTERNAL AND EXTERNAL

The performance of students is evaluated as follows:

Theory
Components Continuous Semester End
Internal Examination
Assessment (SEE)
(CAE)
Marks 40 60
Total Marks 100

Internal Evaluation Component

g. CO-PO Mapping
Course
PO PO PO PO PO PO PO PO PO PO1 PO1 PO1
Outcom PSO1 PSO2 PSO3 PSO4
1 2 3 4 5 6 7 8 9 0 1 2
e

CO1 2 1 1 3 3 1 - - - - - 1 1 1 1 1

CO2 2 1 1 3 3 1 - - - - - 1 1 1 1 1

CO3 2 2 2 2 2 1 - - - - - 2 2 2 2 1

CO4 2 2 2 2 2 1 - - - - - 2 2 2 2 1

CO5 2 1 2 2 2 1 - - - - - 2 1 1 1 1

CO PO correlation matrix of each subject to be mapped with

High correlation (3)
Medium correlation (2)
Low correlation (1)