Soft Computing

Introduction to Soft Computing

4th Semester CSE (AR-21)

1 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Lecture -1

Outline of the Lecture

 About the Course Syllabus, CEO, CO & Assessment Methods.

 Lesson Plan

 Course Overview & Objectives

 Prerequisites

 Introduction to Soft Computing (1st Topic)

2 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 OBJECTIVE
Soft Computing

• This course aims in introducing the concepts in Soft Computing.

• It covers in detail Fuzzy Logic based Systems and applications.
• It also covers Neural Network based Systems and computational
complexity.
• Basic knowledge of Genetic Algorithm based Systems .
• Teaches the neuro-fuzzy hybrid approaches and its applications.

3 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 LEARNING OUTCOME
Soft Computing

Upon completion of this course, students will be able to do the

following:
• Define the Fuzzy Systems.
• Analyze different neural network techniques.
• Understand the Genetic algorithm concepts and its applications.
• Identify the suitable hybrid soft computing technology to solve the complex
problems.

4 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 BOOKS TO FOLLOW
Soft Computing

Text Books:

1. J.S.R.Jang, C.T.Sun and E.Mizutani, “Neuro-Fuzzy and Soft Computing”, Pearson, 2015.

2. Samir Roy, Udit Chakraborty, “Introduction to Soft Computing Neuro-Fuzzy and Genetic Algorithms”, Pearson, 2013

Reference Books:

1. Davis E.Goldberg, “Genetic Algorithms: Search, Optimization and Machine Learning”, Addison Wesley, 2009

2. Kumar S.Ray, “Soft Computing and Its Applications, Volume Two: Fuzzy Reasoning and Fuzzy Control”, CRC Press, 2014

3. Saroj Kaushik Sunita Tiwari, “ Soft Computing : Fundamentals Techniques & Applications”, Tata McGrawHill, 2018

4. Nunes Silva, I., Hernane Spatti, D., Andrade Flauzino, R., Liboni, L.H.B., dos Reis Alves, S.F.,“Artificial Neural Networks - A Practical Course”,
Springer, 2017

5. N.P.Padhy, S.P.Simon, “Soft Computing with MATLAB Programming”, Oxford University Press, 2015

5 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 COURSE TOPICS
Soft Computing

UNIT 1 – Basics of Soft Computing

UNIT 2 – Fuzzy Logic

UNIT 3 - Neural Network

UNIT 4 - Genetic Algorithm

UNIT 5 - Neuro-Fuzzy Modelling

6 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

Soft Computing

UNIT –I
INTRODUCTION

7 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing About the Course Syllabus, CEO, CO & Assessment Methods.

Course Educational Objectives (CEO)

To familiarize with soft computing concepts.
To introduce the ideas of Neural networks, fuzzy logic and use of heuristics based
on human experience.
To introduce the concepts of Genetic algorithm and its applications to soft
computing using some applications.

Course Outcomes (CO)

Upon successful completion of this course, students should be able to:
CO1 Learn about soft computing techniques and their applications and Analyze
various neural network architectures
CO2 Apply fuzzy logic and reasoning to handle uncertainty and solve engineering
problems
CO3 Apply genetic algorithms to combinatorial optimization problems
CO4 Evaluate and compare solutions by various Hybrid soft computing
approaches for a given problem

8 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

Soft Computing About the Course Syllabus, CEO, CO & Assessment Methods.

Course Assessment Methods

1. Two Cycle Test

2. End Semester Examination

3. Online Quizzes, Assignments & Seminars

9 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Lesson Plan
Name Dr. Bidush Kumar Sahoo Designation Associate Professor
Department CSE Semester & Section 4th Semester
Subject Name Introduction to Soft Computing Subject Code BCSOE7051
Pre requisite(s) Algorithms Academic Regulation AR-17
Total Hrs Planned 40 No. of Hrs/week 04 (T-3)
Starting Date 08-01-2024 Total Credit 3
References
Detail Description of Mode of
Unit-I
Hour
No.

Date COs &POs Text Book

Sl.

Topics/Subtopics Lecture
Page No.
1 1.1 Introduction: What is Soft Online [CO1][ PO1] TB1:11,
Computing? Brief descriptions
of different components of
soft computing, Difference
between Hard and soft
computing,

2 1.2 Requirement of Soft Online [CO1][ PO1] TB1:

computing, Major Areas of
Soft Computing, Applications
of Soft Computing.

10 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Lesson Plan

References
Detail Description of Mode of

Unit-
Hour
No.

Date COs &POs Text Book

Sl.

Topics/Subtopics Lecture

I
Page No.
3 1.3 Neural Networks: Basic Online [CO1][ PO1] TB1:11-13
Concept of Neural Networks
4 1.4 Models of an artificial Online [CO1][ PO1] TB1:13-16
Neuron, Various activation
functions
5 1.5 Neural Network Architecture Online [CO1][ PO1] TB1:16-19
& Characteristics, Different
Learning methods
6 1.6 Introduction to Early ANN Online [CO1][ PO1] TB1:19-20
architectures (basics only)
McCulloch & Pitts Model
7 1.7 Perceptron, ADALINE, Online [CO1][ PO1] TB1:22-24
MADALINE
8 1.8 Back Propagation Neural Online [CO1][ PO1] TB1:25-27
Network

11 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Lesson Plan

Detail Description of Mode of References

Unit-
Hour
No.

Date COs &POs Text Book

Sl.

Topics/Subtopics Lecture

I
Page No.
9 1.9 Back propagation Learning Online [CO1][ PO1] TB1:28-30
Algorithm
10 1.10 Example of BPN , Effect of Online [CO1][ PO1] TB1:
Tuning parameters of the
BPN Network,
11 1.11 Associative Memory: Online [CO1][ PO1] TB1:
Autocorrelators,
Hetrocorrelators
12 1.12 Energy function for BAM, Online [CO1][ PO1] TB1:
Exponential BAM.

12 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Lesson Plan

References
Detail Description of Mode of

Unit-
Hour
No.

Date COs &POs Text Book

Sl.

II
Topics/Subtopics Lecture
Page No.
13 2.1 Fuzzy set Vs Crisp sets Online [CO2][ PO1] TB1:
14 2.2 Fuzzy Sets – Properties Online [CO2][ PO1] TB1:
15 2.3 Fuzzy Membership Online [CO2][ PO1] TB1:
Functions
16 2.4 Fuzzy Set Operations Online [CO2][ PO1] TB1:
17 2.5 Crisp and Fuzzy Relations Online [CO2][ PO1] TB1:
18 2.6 Fuzzy Relation Operations Online [CO2][ PO1] TB1:
19 2.7 Crisp logic, Propositional Online [CO2][ PO1] TB1:
logic, Predicate Logic
20 2.8 Fuzzy logic – Quantifier – Online [CO2][ PO1] TB1:
Inference
21 2.9 Fuzzy Rule based system Online [CO2][ PO1] TB1:
22 2.10 Defuzzification Methods Online [CO2][ PO1] TB1:

13 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Lesson Plan

References
Sl. No.

Detail Description of Mode of

Unit-
Hour
Date COs &POs Text Book

III
Topics/Subtopics Lecture
Page No.
23 3.1 Fundamentals of genetic Online [CO1][ PO1] TB1:
algorithms
24 3.2 Encoding, Fitness functions Online [CO1][ PO1] TB1:
25 3.3 Reproduction Online [CO1][ PO1] TB1:
26 3.4 Genetic Modeling: Cross Online [CO1][ PO1] TB1:
over
27 3.5 Different Cross overs Online [CO1][ PO1] TB1:
28 3.6 Inversion and deletion Online [CO1][ PO1] TB1:
29 3.7 Mutation operator Online [CO1][ PO1] TB1:
30 3.8 Bit-wise operators & its Online [CO1][ PO1] TB1:
uses in GA.
31 3.9 Convergence of Genetic Online [CO1][ PO1] TB1:
algorithm
32 3.10 Applications, Real life Online [CO1][ PO1] TB1:
Problems.

14 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Lesson Plan

References
Sl. No.

Detail Description of Mode of

Unit-
Hour
Date COs &POs Text Book

IV
Topics/Subtopics Lecture
Page No.
33 4.1 Hybrid system Online [CO1][ PO1] TB1:
34 4.2 Neural Networks Hybrid Online [CO1][ PO1] TB1:
system
35 4.3 Fuzzy Hybrid system Online [CO1][ PO1] TB1:
36 4.4 Genetic Algorithm Hybrid Online [CO1][ PO1] TB1:
system
37 4.5 Genetic Algorithm based Online [CO1][ PO1] TB1:
Back propagation Networks
38 4.6 GA based weight Online [CO1][ PO1] TB1:
determination
39 4.7 Fuzzy Back Propagation Online [CO1][ PO1] TB1:
Networks
40 4.8 Fuzzy logic controller Online [CO1][ PO1] TB1:

15 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Course Overview & Objectives

This course will cover fundamental concepts used in Soft

computing. The Artificial Neural Networks (ANNs) will be
covered first followed by concepts of Fuzzy logic (FL) and
optimization techniques using Genetic Algorithm (GA).
Applications of different Hybrid Soft Computing techniques to
solve a number of real life problems will be covered to have hands
on practices. In summary, this course will provide exposure to
different soft computing techniques
After completing this course, you will be able to learn:
• Artificial Neural Networks and its Applications.
• Fuzzy Logic and its applications.
• Solving single-objective optimization problems using GAs.
• Solving multi-objective optimization problems using
Evolutionary algorithms (MOEAs).
• Applications of Soft computing to solve problems in
varieties of application domains.
16 Department of CSE, GIET University, Gunupur Thursday, February 27, 20
 Soft Computing Prerequisites

To extract the maximum from the course, the following

prerequisites are required.

 A strong mathematical background.

 Proficiency with algorithms.

 Programming skills in C, C++, Python or Java.

 Critical thinking and problem solving skills.

17 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Introduction to Soft Computing

 Concept of Computation
 Soft Computing Techniques
 Hard computing
 Soft computing
 How soft computing?
 Hard computing vs. Soft computing

18 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing CONCEPT OF COMPUTATION

Computin
Antecedent g Consequent
y = f(x)
Control Action
Figure: Basic of computing
Antecedent: A thing that existed before or logically precedes another.
y = f(x), f is a mapping function, f is also called formal methods
or an Algorithm to solve the problem
Control Action should an unambiguous and accurate.
Consequent: Following as a result or effect.
It should provide precise solution.
It is suitable for problem, which is easy to model mathematically.
19 Department of CSE, GIET University, Gunupur Thursday, February 27, 20
 Soft Computing Soft Computing Techniques

Neural
Neuro Fuzzy Network Neuro Genetic

Neuro Fuzzy
Genetic
Fuzzy Genetic
Logic Algorithm

Fuzzy Genetic

20 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Soft Computing Techniques

Soft Computing refers to a consortium of computational

methodologies. Some of its principal components include Neural
Networks (NN), Fuzzy Logic (FL) and Genetic Algorithms (GA), all
having their roots in Artificial Intelligence (Al).

Also, a combination of one or more of the methodologies mentioned

termed hybrid systems has resulted in the emergence of a new class
of systems such as Neuro‑Fuzzy, Fuzzy‑Genetic, Neuro‑Genetic and
Neuro‑Fuzzy-Genetic systems.

“Artificial Intelligence (AI) is an area of computer science concerned

with designing intelligent computer systems” that is, systems that
exhibit the characteristics we associate with intelligence in human
behavior. “Al is a branch of computer science that is concerned with
the automation of intelligent behavior”.

21 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing

22 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Hard Computing

• In 1996, L. A. Zade (LAZ) introduced the term Hard

Computing.
• According to LAZ: We term a computing as Hard
computing, if
 Precise result is guaranteed.
 Control action is Unambiguous.
 Control action is formally defined (i.e., with
mathematical model or algorithm).

23 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Examples of Hard Computing

• Solving numerical problems (e.g., roots of polynomials,

integration, etc.).

• Searching and sorting techniques.

• Solving computational geometry problems (e.g., shortest tour

in a graph, finding closet pair of points given a set of points,
etc.) many more…

24 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Soft Computing
The term soft computing was proposed by the inventor of fuzzy
logic, Lotfi A. Zadeh. He describes it as follows.
Soft computing is a collection of methodologies that aim to exploit
the tolerance for imprecision and uncertainty to achieve tractability,
robustness, and low solution cost. Its principal constituents are fuzzy
logic, neuro-computing, and probabilistic reasoning. The role model
for soft computing is the human mind.
• It does not require any mathematical modeling of problem
solving.
• It may not yield the precise solution.
• Algorithms are adaptive (i.e., it can adjust to the change of
dynamic environment).
• Use some biological inspired methodologies such as genetics,
evolution, Ant’s behaviors, particles swarming, human nervous
system, etc.).
25 Department of CSE, GIET University, Gunupur Thursday, February 27, 20
 Soft Computing

Soft computing

Example: Hand written character recognition

(Artificial Neural Networks)

26 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing

Example: Robot movement

(Fuzzy Logic)
27 Department of CSE, GIET University, Gunupur Thursday, February 27, 20
 Soft Computing

Bank with
Soft computing maximum
return

Example: Money allocation problem

(Evolutionary Computing)

28 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing How soft computing?

 How a student learns from his/her teacher?

• Teacher asks questions and tell the answers then.
• Teacher puts questions and hints answers and asks
whether the answers are correct or not.
• Student thus learn a topic and store in his memory.
• Based on the knowledge he solves new problems.

 This is the way how human brain works.

 Based on this concept Artificial Neural Network is used to

solve the problems.

29 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing How soft computing?

 How a doctor treats his patient?

• Doctor asks the patient about suffering.
• Doctor find the symptoms of diseases.
• Doctor prescribed tests and medicines.

 This is exactly the way Fuzzy Logic works.

• Symptoms are correlated with diseases with uncertainty.
• Doctor prescribes tests/medicines fuzzily.

30 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing How soft computing?

 How world selects the best?

• It starts with a population (random).
• Reproduces another population (next generation).
• Rank the population and selects the superior
individuals.

 Genetic algorithm is based on this natural phenomena.

• Population is synonymous to solutions.
• Selection of superior solution is synonymous to
exploring the optimal solution.

31 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Hard computing vs. Soft computing
Hard computing Soft computing
 It requires a precisely stated  It is tolerant of imprecision,
analytical model and often a uncertainty, partial truth, and
lot of computation time. approximation.
 It is based on binary logic,  It is based on fuzzy logic,
crisp systems, numerical neural nets and probabilistic
analysis and crisp software. reasoning.
 It has the characteristics of  It has the characteristics of
precision and categoricity. approximation &
dispositionality.
 It is deterministic.  It incorporates stochasticity.

 It is strictly sequential.  It allows parallel

computations.

32 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Hard computing vs. Soft computing

Hard computing Soft computing

 It requires exact input data.  It can deal with ambiguous
and noisy data.
 It produces precise answers.  It can yield approximate
answers
 It requires programs to be  It can evolve its own
written programs

33 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Question Answers

1. Core components of soft Computing are

a) Neural Network, Fuzzy Logic and Genetic Algorithms

b) Fuzzy Networks and Artificial Intelligence
c) Artificial Intelligence and Neural Science
d) Neural Science and Genetic Science

Answer: a

34 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Question Answers

2. Who initiated the idea of Soft Computing

a) Charles Darwin
b) Lofti A Zadeh
c) Rechenberg
d) Mc_Culloch

Answer: b

35 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Question Answers

3. Hand written character recognition can use which

technique?

a) Neural Network
b) Fuzzy Logic
c) Genetic Algorithm
d) Evolutionary Computing

Answer: a

36 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing Question Answers Session

37 Department of CSE, GIET University, Gunupur Thursday, February 27, 20

 Soft Computing

38 Department of CSE, GIET University, Gunupur Thursday, February 27, 20