UNIVERSITY INSTITUTE OF ENGINEERING

DEPARTMENT OF AIT - CSE

Bachelor of Engineering (CSE)
SOFT COMPUTING (22CSH-345 )
By: Ms. Aarti (E15380)

DISCOVER . LEARN . EMPOWER

 COURSE DESCRIPTION
• Soft Computing is dedicated to system solutions based on soft computing paradigms.

• The course provides an understanding of soft computing techniques such as genetic

programming, swarm intelligence, neural science, neural net systems, fuzzy set theory,
fuzzy systems.

• The approaches of soft computing course enable solutions for problems that may be
either unsolvable or just too time-consuming to solve with the current hardware.

• Soft computing is tolerant of partial truths, uncertainty, imprecision and

approximation, unlike traditional computing models. The tolerance of soft computing
allows researchers working in this particular field to solve the problems that traditional
computing approaches can't process and solve.
2
 Course Objectives
To introduce soft computing concepts and techniques of artificial neural networks,
fuzzy sets, fuzzy logic and genetic algorithms

To understand the various techniques from the application point of view.

To analyze various soft computing techniques and decide the technique to be used in
a particular problem situation.

To implement soft computing based solutions for real-world problems

3
 Course Outcomes
CO1 Identify and describe soft computing techniques and their roles 1
in building intelligent machines

CO2 Recognize the feasibility of applying a soft computing 2,4

methodology for a particular problem.

CO3 Apply fuzzy logic and reasoning to handle uncertainty and solve 3
engineering 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 3
using a soft computing approach.

CO5 Evaluate various soft computing approaches for a given 4

problem.
4
 Internal Evaluation Component

SNo. Type of Assessment Weightage of actual Frequency of Task Final Weightage in Remarks
conduct Internal (Graded/Non-
Assessment Graded)
1 Assignment 10 marks of each One per unit 10 marks Graded
assignment
2 Quiz 4 marks of each quiz One per unit 4 marks Graded

3 Time Bound Quiz 12 marks for each test One per unit 12 marks Graded

4 Case study NA One per unit NA Non-Graded

5 Discussion Forum 4 marks One per unit 4 marks Graded

6 Presentation NA NA NA NA
7 Mid-Sem Test 20 Marks for one MST 2 per semester 20 marks Graded

8 Attendance and NA NA 2 NA
Engagement Score on
BB

5
 What is computing ???
• Computing refers to the use of computer technology to solve
problems, perform calculations, process data, and make
decisions. Traditional computing primarily relies on precise
mathematical models and algorithms to derive solutions.

6
What is "Soft" in Soft Computing?

Soft Computing (SC) is a branch of computing that deals with

approximations and uncertainty rather than strict precision. It aims to
handle complex and ambiguous real-world problems, where traditional
computing methods may not be effective.
The term "soft" is used to indicate the flexibility, adaptability, and
tolerance for imprecision and uncertainty that characterizes soft
computing approaches.

7
8
 Some characteristics of Soft computing
• Approximation: Soft computing methods focus on approximating solutions
rather than finding exact solutions. This allows for efficient handling of complex
problems.
• Tolerance for Uncertainty: SC techniques can handle incomplete or noisy data,
making them suitable for real-world applications where data may not always be
precise.
• Adaptability: Soft computing approaches are adaptive and can learn from
experience or adjust their parameters based on feedback, enhancing their
problem-solving abilities.
• Robustness: Soft computing methods are resilient to noise or perturbations in the
data, making them suitable for handling unpredictable real-world scenarios.
• Human-Like Decision Making: SC models often mimic human-like decision-
making processes, such as fuzzy logic and neural networks, which can provide
more intuitive and human-understandable outcomes.It is based on Fuzzy logic,
genetic algorithms, machine learning, ANN, and expert systems. 9
Some of it’s principle components includes:

• Neural Network(NN)
• Fuzzy Logic(FL)
• Genetic Algorithm(GA)

10
Summary
• Discussed about Soft Computing and Hard Computing
• Discussed about applications of Soft Computing

11
 Post Lecture Discussion
1. Describe the meaning of “Soft” in “Soft Computing”.
2. What techniques comes under the Soft Computing.

12
 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.
13
 References

Online Video Link

• https://onlinecourses.nptel.ac.in/noc22_cs54/preview
• https://archive.nptel.ac.in/courses/106/105/106105173/
• Text Book
• Bart Kosko, “Neural Network and Fuzzy Systems: A Dynamic System Approach to Machine” Prentice-Hall 1998

• L. Fausett, “Fundamentals of Neural Networks: Architectures, Algorithms, and Applications”, Prentice-Hall, 1994.

• Jack M. Zurada, “Introduction to Artificial Neural Systems”, PWS Publishing Co., Boston, 2000.

• J S R Jang, “Neuro-Fuzzy & Soft Computing,”, Pearson.

14
THANK YOU

For Queries:
[email protected]

15