INDUS INSTITUTE OF TECHNOLOGY& ENGINEERING
Constituent Institute of Indus University
Subject: Soft Computing
Program: B. Tech CE/CSE/IT Subject Code: CE0719 Semester: VII
Teaching Scheme (Hours per week) Examination Evaluation Scheme (Marks)
Continuous Continuous
University University Internal Internal
Lecture Tutorial Practical Credits Theory Practical Evaluation Evaluation Total
Examination Examination (CIE)- (CIE)-
Theory Practical
3 0 2 4 40 40 60 60 200
Course Objectives:
1. Soft computing refers to principal components like fuzzy logic, neural networks and
genetic algorithm, which have their roots in Artificial Intelligence.
2. Healthy integrations of all these techniques have resulted in extending the capabilities
of the technologies to more effective and efficient problem-solving methodologies
3. To know basic idea of modern engineering techniques which are useful for solving
non-linear andcomplex functions that may come across dissertation/research work which
further helps in employability and entrepreneurship.
4. To solve various optimization problems and to implement algorithms based on soft
computing.
5. To understand different soft computing techniques like Genetic Algorithms, Fuzzy
Logic, NeuralNetworks and their combination.
6. To apply soft computing techniques to solve engineering or real-life problems for skill
development.
CONTENTS
UNIT-I
[12 hours]
Introduction to Neural Network: Biological Neuron, Fundamental concept of Artificial Neural
Network & Biological Neural Network , Evolution of Neural Networks, Basic Models of
Artificial Neural Networks ,Types of Learning, Important Terminologies of ANNs ,Idea of
computational units & Activation Functions, McCulloch–Pitts unit and Thresholding logic,
Linear separability, Hebb network
UNIT-II
[12 hours]
Supervised Learning Networks: Perceptron, Perceptron Learning Algorithm, Convergence
theorem for Perceptron Learning Algorithm, Adaline ,Multiple Adaptive Linear Neurons ,
Multi-layered Networks, Generalized delta rule, Gradient Descent, Backpropagation Network,
Radial basis function network, Adaptive Learning rate, Feedback Networks, Back-propagation
through time, real-time recurrent learning
Unsupervised Learning Networks: Competitive Learning, Fixed weight Competitive Nets,
Kohonen Self-organizing Feature Maps, Extended Kohonen SOM.
UNIT-III
[12 hours]
Fuzzy Logic: Basic concepts of fuzzy logic, Fuzzy sets and Crisp sets, Fuzzy set theory and
operations, Properties of fuzzy sets, Fuzzy and Crisp relations, Fuzzy to Crisp conversion. Fuzzy
Logic –II (Fuzzy Membership, Rules) Membership functions, interference in fuzzy logic, fuzzy
if-then rules, Fuzzy implications and Fuzzy algorithms, Fuzzyfication & Defuzzificataion, Fuzzy
Controller, Industrial applications
UNIT-IV
[12 hours]
Genetic Algorithm(GA) :Basic concepts, working principle, procedures of GA, flow chart of
GA, Genetic representations, (encoding) Initialization and selection, Selection techniques,
Crossover Techniques, ,Genetic operators, Mutation, Mutation techniques ,Problem Solving
using GA, applications.
Course Outcomes:
At the end of this subject, students should be able to:
1. Identify and describe soft computing techniques and their roles in building intelligent
machines.
2. Recognize the feasibility of applying a soft computing methodology for a particular
problem.
3. Apply fuzzy logic and reasoning to handle uncertainty and solve engineering problems.
4. Apply genetic algorithms to combinatorial optimization problems.
5. Apply neural networks to pattern classification and regression problems.
6. Effectively use existing software tools to solve real problems using a soft computing
approach.
Text Books:
1. S.N. Sivanandan and S.N. Deepa, Principles of Soft Computing, Wiley India, 2007.
ISBN: 10: 81-265-1075-7.
2. S. Rajsekaran & G.A. Vijayalakshmi Pai, “Neural Networks, Fuzzy Logic and Genetic
Algorithm:Synthesis and Applications” Prentice Hall of India.
Reference Books:
1. Simon Haykin,”NeuralNetowrks”, Prentice Hall of India
2. Timothy J. Ross, “Fuzzy Logic with Engineering Applications” Wiley India.
3. Kumar Satish, “Neural Networks” Tata Mc Graw Hill
Web Resources
1. [Link]
2. [Link]
3. [Link]
4. [Link]
LIST OF EXPERIMENTS
Experi Title Learning Outcomes
ment.
No.
W.A.P to implement simple AND & OR function with Basic knowledge of
1 neuron.(take w1=w2=1, find appropriate neuron model.
threshold(threshold)
Write a program to generate XOR function using Basic knowledge of
2 McCulloch-Pitts neuron and appropriate values for neuron model.
weights, bias and threshold.
Write a program for perceptron net for an AND function Basic knowledge of
3 with bipolar inputs and targets. perceptron learning
algorithm.
Basic knowledge of
4 Write a program to Implement Hebb Algorithm. hebb algorithm in
In neural network.
Basic knowledge of
ADALINE algorithm
5 Write a program to Implement ADALINE Algorithm.
in
In neural network.
Basic knowledge of
MADALINE
6 Write a program to Implement MADALINE Algorithm.
algorithm in
In neural network.
Basic knowledge of
Write a program to Implement BPN(Back Propagation back propogation
7
Network) Algorithm. algorithm in
In neural network.
Basic knowledge of
8 W.A.P to implement fuzzy set properties & operations. fuzzy logic.
Solve a given problem-1(Operatons) using Fuzzy Logic in Basic knowledge of
9 MATLAB. fuzzy logic.
Solve a given problem (Max-Min Composition) using Basic knowledge of
10 Fuzzy Logic in MATLAB. fuzzy logic.
Solve a given problem using fuzzy inference in MATLB Basic knowledge of
11 GUI fuzzy logic.
W.A.P to maximize the function f(x) =x2 using Genetic Basic knowledge of
12 algorithm, where x ranges from (0-31),perform 5 Genetic Algorithm.
iterations.
Basic knowledge of
W.A.P to find the minimum of the quadratic equation
13 Genetic Algorithm.
f(x)=x2+5x+2, within the range -6<=x<=0
Basic knowledge of
Study GA tool in MATLAB.
14 Genetic Algorithm.
Study Neural Network tool in MATLAB. Basic knowledge of
15
neuron network.
