# Principles of Soft Computing, 3ed

ISBN: 9788126577132

788 pages

eBook also available for institutional users

## Description

This book is meant for a wide range of readers, who wish to learn the basic concepts of soft computing. It can also be useful for programmers, researchers and management experts who use soft computing techniques. The basic concepts of soft computing are dealt in detail with the relevant information and knowledge available for understanding the computing process. The various neural network concepts are explained with examples, highlighting the difference between various architectures. Fuzzy logic techniques have been clearly dealt with suitable examples. Genetic algorithm operators and the various classifications have been discussed in lucid manner, so that a starter can understand the concepts with a minimal effort.

Chapter 1 Introduction

1.1 Neural Networks

1.2 Application Scope of Neural Networks

1.3 Fuzzy Logic

1.4 Genetic Algorithm

1.5 Hybrid Systems

1.6 Soft Computing

1.7 Summary

Chapter 2 Artificial Neural Network: An Introduction

2.1 Fundamental Concept

2.2 Evolution of Neural Networks

2.3 Basic Models of Artificial Neural Network

2.4 Important Terminologies of ANNs

2.5 McCulloch–Pitts Neuron

2.6 Linear Separability

2.7 Hebb Network

2.8 Summary

2.9 Solved Problems

2.10 Review Questions

2.11 Exercise Problems

2.12 Projects

Chapter 3 Supervised Learning Network

3.1 Introduction

3.2 Perceptron Networks

3.3 Adaptive Linear Neuron (Adaline)

3.4 Multiple Adaptive Linear Neurons

3.5 Back-Propagation Network

3.6 Radial Basis Function Network

3.7 Time Delay Neural Network

3.8 Functional Link Networks

3.9 Tree Neural Networks

3.10 Wavelet Neural Networks

3.11 Summary

3.12 Solved Problems

3.13 Review Questions

3.14 Exercise Problems

3.15 Projects

Chapter 4 Associative Memory Networks

4.1 Introduction

4.2 Training Algorithms for Pattern Association

4.3 Autoassociative Memory Network

4.4 Heteroassociative Memory Network

4.5 Bidirectional Associative Memory (BAM)

4.6 Hopfield Networks

4.7 Iterative Autoassociative Memory Networks

4.8 Temporal Associative Memory Network

4.9 Summary

4.10 Solved Problems

4.11 Review Questions

4.12 Exercise Problems

4.13 Projects

Chapter 5 Unsupervised Learning Networks

5.1 Introduction

5.2 Fixed Weight Competitive Nets

5.3 Kohonen Self-Organizing Feature Maps

5.4 Learning Vector Quantization

5.5 Counterpropagation Networks

5.6 Adaptive Resonance Theory Network

5.7 Summary

5.8 Solved Problems

5.9 Review Questions

5.10 Exercise Problems

5.11 Projects

Chapter 6 Special Networks

6.1 Introduction

6.2 Simulated Annealing Network

6.3 Boltzmann Machine

6.4 Gaussian Machine

6.5 Cauchy Machine

6.6 Probabilistic Neural Net

6.7 Cascade Correlation Network

6.8 Cognitron Network

6.9 Neocognitron Network

6.10 Cellular Neural Network

6.11 Logicon Projection Network Model

6.12 Spatio-Temporal Connectionist Neural Network

6.13 Optical Neural Networks

6.14 Neuroprocessor Chips

6.15 Ensemble Neural Network Models

6.16 Summary

6.17 Review Questions

Chapter 7 Third-Generation Neural Networks

7.1 Introduction

7.2 Spiking Neural Networks

7.3 Convolutional Neural Networks

7.4 Deep Learning Neural Networks

7.5 Extreme Learning Machine Model

7.6 Summary

7.7 Review Questions

Chapter 8 Clustering of Self-Organizing Feature Maps

8.1 Introduction

8.2 Concept of Clustering

8.3 Training of SOMs

8.4 Clustering of SOM: Method I

8.5 Clustering of SOM: Method II

8.5 Summary

8.6 Review Questions

Chapter 9 Stability Analysis of a Class of Artificial Neural Network Systems

9.1 Introduction

9.2 Stability Conditions of a Class of Non-Linear Systems

9.3 Formation of Main Matrices and Sub-Matrices for an Artificial Neural Network System

9.4 Methodology Developed for Stability Analysis of Artificial Neural Networks

9.5 Summary

9.6 Solved Problems

9.7 Review Questions

9.8 Exercise Problems

Chapter 10 Introduction to Fuzzy Logic, Classical Sets and Fuzzy Sets

10.1 Introduction to Fuzzy Logic

10.2 Classical Sets (Crisp Sets)

10.3 Fuzzy Sets

10.4 Summary

10.5 Solved Problems

10.6 Review Questions

10.7 Exercise Problems

Chapter 11 Classical Relations and Fuzzy Relations

11.1 Introduction

11.2 Cartesian Product of Relation

11.3 Classical Relation

11.4 Fuzzy Relations

11.5 Tolerance and Equivalence Relations

11.6 Noninteractive Fuzzy Sets

11.7 Summary

11.8 Solved Problems

11.9 Review Questions

11.10 Exercise Problems

Chapter 12 Membership Function

12.1 Introduction

12.2 Features of the Membership Functions

12.3 Fuzzification

12.4 Methods of Membership Value Assignments

12.5 Summary

12.6 Solved Problems

12.7 Review Questions

12.8 Exercise Problems

Chapter 13 Defuzzification

13.1 Introduction

13.2 Lambda-Cuts for Fuzzy Sets (Alpha-Cuts)

13.3 Lambda-Cuts for Fuzzy Relations

13.4 Defuzzification Methods

13.5 Summary

13.6 Solved Problems

13.7 Review Questions

13.8 Exercise Problems

Chapter 14 Fuzzy Arithmetic and Fuzzy Measures

14.1 Introduction

14.2 Fuzzy Arithmetic

14.3 Extension Principle

14.4 Fuzzy Measures

14.5 Measures of Fuzziness

14.6 Fuzzy Integrals

14.7 Summary

14.8 Solved Problems

14.9 Review Questions

14.10 Exercise Problems

Chapter 15 Fuzzy Rule Base and Approximate Reasoning

15.1 Introduction

15.2 Truth Values and Tables in Fuzzy Logic

15.3 Fuzzy Propositions

15.4 Formation of Rules

15.5 Decomposition of Rules (Compound Rules)

15.6 Aggregation of Fuzzy Rules

15.7 Fuzzy Reasoning (Approximate Reasoning)

15.8 Fuzzy Inference Systems (FIS)

15.9 Overview of Fuzzy Expert System

15.10 Summary

15.11 Review Questions

15.12 Exercise Problems

Chapter 16 Fuzzy Decision Making

16.1 Introduction

16.2 Individual Decision Making

16.3 Multiperson Decision Making

16.4 Multiobjective Decision Making

16.5 Multiattribute Decision Making

16.6 Fuzzy Bayesian Decision Making

16.7 Summary

16.8 Review Questions

16.9 Exercise Problems

Chapter 17 Fuzzy Logic Control Systems

17.1 Introduction

17.2 Control System Design

17.3 Architecture and Operation of FLC System

17.4 FLC System Models

17.5 Application of FLC Systems

17.6 Summary

17.7 Review Questions

17.8 Exercise Problems

Chapter 18 Fuzzy Cognitive Maps

18.1 Cognitive Maps – Base for FCM

18.2 Fundamentals of FCM

18.3 Dynamics of FCM and Its Activation Function

18.4 Applications of FCM

18.5 Summary

18.6 Review Questions

Chapter 19 Type-2 Fuzzy Sets and Embedded Fuzzy Sets

19.1 Basic Concepts and Definition of Type-2 Fuzzy Sets

19.2 Set Theoretic and Algebraic Operations on Type-2 Fuzzy Sets

19.3 Properties of Membership Grades

19.4 Cartesian Product of Type-2 Fuzzy Sets

19.5 Composition of Type-2 Fuzzy Sets

19.6 Interval Type-2 Fuzzy Sets

19.7 Applications of Type-2 Fuzzy Sets

19.8 Embedded Fuzzy Sets

19.9 Summary

19.10 Review Questions

Chapter 20 Stability Analysis of Certain Classes of Fuzzy Systems

20.1 Stability Analysis of Fuzzy Systems given by System Matrices

20.2 Numerical Illustrations for Fuzzy System Stability

20.3 Stability Analysis of Fuzzy Systems represented by Relational Matrices

20.4 Stabilization and Stability Analysis of an Inverted Pendulum Motion using Fuzzy Logic Controller

20.5 Summary

20.6 Review Questions

20.7 Exercise Problems

Chapter 21 Genetic Algorithm

21.1 Introduction

21.2 Biological Background

21.3 Traditional Optimization and Search Techniques

21.4 Genetic Algorithm and Search Space

21.5 Genetic Algorithm vs. Traditional Algorithms

21.6 Basic Terminologies in Genetic Algorithm

21.7 Simple GA

21.8 General Genetic Algorithm

21.9 Operators in Genetic Algorithm

21.10 Stopping Condition for Genetic Algorithm Flow

21.11 Constraints in Genetic Algorithm

21.12 Problem Solving Using Genetic Algorithm

21.13 The Schema Theorem

21.14 Classification of Genetic Algorithm

21.15 Holland Classifier Systems

21.16 Genetic Programming

21.17 Advantages and Limitations of Genetic Algorithm

21.18 Applications of Genetic Algorithm

21.19 Summary

21.20 Review Questions

21.21 Exercise Problems

Chapter 22 Differential Evolution Algorithm

22.1 Differential Evolution – Process Flow and Operators

22.2 Selection of DE Control Parameters

22.3 Schemes of Differential Evolution

22.4 Numerical Illustration of DE Algorithm for a Simple Function Optimization

22.5 Applications of Differential Evolution

22.6 Summary

22.7 Review Questions

Chapter 23 Hybrid Soft Computing Techniques

23.1 Introduction

23.2 Neuro-Fuzzy Hybrid Systems

23.3 Genetic Neuro-Hybrid Systems

23.4 Genetic Fuzzy Hybrid and Fuzzy Genetic Hybrid Systems

23.5 Simplified Fuzzy ARTMAP

23.6 Summary

23.7 Solved Problems using MATLAB

23.8 Review Questions

23.9 Exercise Problems xxiv

Chapter 24 Applications of Soft Computing

24.1 Introduction

24.2 A Fusion Approach of Multispectral Images with SAR (Synthetic Aperture Radar) Image for Flood Area

24.3 Optimization of Traveling Salesman Problem using Genetic Algorithm Approach

24.4 Genetic Algorithm-Based Internet Search Technique

24.5 Soft Computing Based Hybrid Fuzzy Controllers

24.6 Soft Computing Based Rocket Engine Control

24.7 Summary

24.8 Review Questions

24.9 Exercise Problems

Chapter 25 Soft Computing Techniques Using C and C++

25.1 Introduction

25.2 Neural Network Implementation

25.3 Fuzzy Logic Implementation

25.4 Genetic Algorithm Implementation

25.5 Summary

25.6 Exercise Problems

Chapter 26 MATLAB Environment for Soft Computing Technique

26.1 Introduction

26.2 Getting Started with MATLAB

26.3 Introduction to Simulink

26.4 MATLAB Neural Network Toolbox

26.5 Fuzzy Logic MATLAB Toolbox

26.6 Genetic Algorithm MATLAB Toolbox

26.7 Neural Network MATLAB Source Codes

26.8 Fuzzy Logic MATLAB Source Codes

26.9 Genetic Algorithm MATLAB Source Codes

26.10 Summary

26.11 Exercise Problems

Bibliography

Sample Question Paper 1

Sample Question Paper 2

Sample Question Paper 3

Sample Question Paper 4

Sample Question Paper 5

Index xx