You are previewing Soft Computing.
O'Reilly logo
Soft Computing

Book Description

Soft computing is a branch of computer science that deals with a family of methods that imitate human intelligence. This is done with the goal of creating tools that will contain some human-like capabilities (such as learning, reasoning and decision-making). This book covers the entire gamut of soft computing, including fuzzy logic, rough sets, artificial neural networks, and various evolutionary algorithms. It offers a learner-centric approach where each new concept is introduced with carefully designed examples/instances to train the learner.

Table of Contents

  1. Cover
  2. Title page
  3. Contents
  4. About the Authors
  5. Dedication
  6. Preface
  7. Chapter 1: Introduction
    1. 1.1 What is Soft Computing?
    2. 1.2 Fuzzy Systems
    3. 1.3 Rough Sets
    4. 1.4 Artificial Neural Networks
    5. 1.5 Evolutionary Search Strategies
    6. Chapter Summary
    7. Test Your Knowledge
    8. Answers
    9. Exercises
    10. Bibliography and Historical Notes
  8. Chapter 2: Fuzzy Sets
    1. 2.1 Crisp Sets: A Review
      1. 2.1.1 Basic Concepts
      2. 2.1.2 Operations on Sets
      3. 2.1.3 Properties of Sets
    2. 2.2 Fuzzy Sets
      1. 2.2.1 Fuzziness/Vagueness/Inexactness
      2. 2.2.2 Set Membership
      3. 2.2.3 Fuzzy Sets
      4. 2.2.4 Fuzzyness vs. Probability
      5. 2.2.5 Features of Fuzzy Sets
    3. 2.3 Fuzzy Membership Functions
      1. 2.3.1 Some Popular Fuzzy Membership Functions
      2. 2.3.2 Transformations
      3. 2.3.3 Linguistic Variables
    4. 2.4 Operations on Fuzzy Sets
    5. 2.5 Fuzzy Relations
      1. 2.5.1 Crisp Relations
      2. 2.5.2 Fuzzy Relations
      3. 2.5.3 Operations on Fuzzy Relations
    6. 2.6 Fuzzy Extension Principle
      1. 2.6.1 Preliminaries
      2. 2.6.2 The Extension Principle
    7. Chapter Summary
    8. Solved Problems
    9. Test Your Knowledge
    10. Answers
    11. Exercises
    12. Bibliography and Historical Notes
  9. Chapter 3: Fuzzy Logic
    1. 3.1 Crisp Logic: A Review
      1. 3.1.1 Propositional Logic
      2. 3.1.2 Predicate Logic
      3. 3.1.3 Rules of Inference
    2. 3.2 Fuzzy Logic Basics
      1. 3.2.1 Fuzzy Truth Values
    3. 3.3 Fuzzy Truth in Terms of Fuzzy Sets
    4. 3.4 Fuzzy Rules
      1. 3.4.1 Fuzzy If-Then
      2. 3.4.2 Fuzzy If-Then-Else
    5. 3.5 Fuzzy Reasoning
      1. 3.5.1 Fuzzy Quantifiers
      2. 3.5.2 Generalized Modus Ponens
      3. 3.5.3 Generalized Modus Tollens
    6. Chapter Summary
    7. Solved Problems
    8. Test Your Knowledge
    9. Answers
    10. Exercises
    11. Bibliography and Historical Notes
  10. Chapter 4: Fuzzy Inference Systems
    1. 4.1 Introduction
    2. 4.2 Fuzzification of the Input Variables
    3. 4.3 Application of Fuzzy Operators on the Antecedent Parts of the Rules
    4. 4.4 Evaluation of the Fuzzy Rules
    5. 4.5 Aggregation of Output Fuzzy Sets Across the Rules
    6. 4.6 Defuzzification of the Resultant Aggregate Fuzzy Set
      1. 4.6.1 Centroid Method
      2. 4.6.2 Centre-of-Sums (CoS) Method
      3. 4.6.3 Mean-of-Maxima (MoM) Method
    7. 4.7 Fuzzy Controllers
      1. 4.7.1 Fuzzy Air Conditioner Controller
      2. 4.7.2 Fuzzy Cruise Controller
    8. Chapter Summary
    9. Solved Problems
    10. Test Your Knowledge
    11. Answers
    12. Exercises
    13. Bibliography and Historical Notes
  11. Chapter 5: Rough Sets
    1. 5.1 Information Systems and Decision Systems
    2. 5.2 Indiscernibility
    3. 5.3 Set Approximations
    4. 5.4 Properties of Rough Sets
    5. 5.5 Rough Membership
    6. 5.6 Reducts
    7. 5.7 Application
    8. Chapter Summary
    9. Solved Problems
    10. Test Your Knowledge
    11. Answers
    12. Exercises
    13. Bibliography and Historical Notes
  12. Chapter 6: Artificial Neural Networks: Basic Concepts
    1. 6.1 Introduction
      1. 6.1.1 The Biological Neuron
      2. 6.1.2 The Artificial Neuron
      3. 6.1.3 Characteristics of the Brain
    2. 6.2 Computation in Terms of Patterns
      1. 6.2.1 Pattern Classification
      2. 6.2.2 Pattern Association
    3. 6.3 The McCulloch–Pitts Neural Model
    4. 6.4 The Perceptron
      1. 6.4.1 The Structure
      2. 6.4.2 Linear Separability
      3. 6.4.3 The XOR Problem
    5. 6.5 Neural Network Architectures
      1. 6.5.1 Single Layer Feed Forward ANNs
      2. 6.5.2 Multilayer Feed Forward ANNs
      3. 6.5.3 Competitive Network
      4. 6.5.4 Recurrent Networks
    6. 6.6 Activation Functions
      1. 6.6.1 Identity Function
      2. 6.6.2 Step Function
      3. 6.6.3 The Sigmoid Function
      4. 6.6.4 Hyperbolic Tangent Function
    7. 6.7 Learning by Neural Nets
      1. 6.7.1 Supervised Learning
      2. 6.7.2 Unsupervised Learning
    8. Chapter Summary
    9. Solved Problems
    10. Test Your Knowledge
    11. Answers
    12. Exercises
    13. Bibliography and Historical Notes
  13. Chapter 7: Pattern Classifiers
    1. 7.1 Hebb Nets
    2. 7.2 Perceptrons
    3. 7.3 ADALINE
    4. 7.4 MADALINE
    5. Chapter Summary
    6. Solved Problems
    7. Test Your Knowledge
    8. Answers
    9. Exercises
    10. Bibliography and Historical Notes
  14. Chapter 8: Pattern Associators
    1. 8.1 Auto-associative Nets
      1. 8.1.1 Training
      2. 8.1.2 Application
      3. 8.1.3 Elimination of Self-connection
      4. 8.1.4 Recognition of Noisy Patterns
      5. 8.1.5 Storage of Multiple Patterns in an Auto-associative Net
    2. 8.2 Hetero-associative Nets
      1. 8.2.1 Training
      2. 8.2.2 Application
    3. 8.3 Hopfield Networks
      1. 8.3.1 Architecture
      2. 8.3.2 Training
    4. 8.4 Bidirectional Associative Memory
      1. 8.4.1 Architecture
      2. 8.4.2 Training
      3. 8.4.3 Application
    5. Chapter Summary
    6. Solved Problems
    7. Test Your Knowledge
    8. Answers
    9. Exercises
    10. Bibliography and Historical Notes
  15. Chapter 9: Competitive Neural Nets
    1. 9.1 The MAXNET
      1. 9.1.1 Training a MAXNET
      2. 9.1.2 Application of MAXNET
    2. 9.2 Kohonen’s Self-organizing Map (SOM)
      1. 9.2.1 SOM Architecture
      2. 9.2.2 Learning by Kohonen’s SOM
      3. 9.2.3 Application
    3. 9.3 Learning Vector Quantization (LVQ)
      1. 9.3.1 LVQ Learning
      2. 9.3.2 Application
    4. 9.4 Adaptive Resonance Theory (ART)
      1. 9.4.1 The Stability-Plasticity Dilemma
      2. 9.4.2 Features of ART Nets
      3. 9.4.3 ART 1
    5. Chapter Summary
    6. Solved Problems
    7. Test Your Knowledge
    8. Answers
    9. Exercises
    10. Bibliography and Historical Notes
  16. Chapter 10: Backpropagation
    1. 10.1 Multi-layer Feedforward Net
      1. 10.1.1 Architecture
      2. 10.1.2 Notational Convention
      3. 10.1.3 Activation Functions
    2. 10.2 The Generalized Delta Rule
    3. 10.3 The Backpropagation Algorithm
      1. 10.3.1 Choice of Parameters
      2. 10.3.2 Application
    4. Chapter Summary
    5. Solved Problems
    6. Test Your Knowledge
    7. Answers
    8. Exercises
    9. Bibliography and Historical Notes
  17. Chapter 11: Elementary Search Techniques
    1. 11.1 State Spaces
    2. 11.2 State Space Search
      1. 11.2.1 Basic Graph Search Algorithm
      2. 11.2.2 Informed and Uninformed Search
    3. 11.3 Exhaustive Search
      1. 11.3.1 Breadth-first Search (BFS)
      2. 11.3.2 Depth-first Search (DFS)
      3. 11.3.3 Comparison Between BFS and DFS
      4. 11.3.4 Depth-first Iterative Deepening
      5. 11.3.5 Bidirectional Search
      6. 11.3.6 Comparison of Basic Uninformed Search Strategies
    4. 11.4 Heuristic Search
      1. 11.4.1 Best-first Search
      2. 11.4.2 Generalized State Space Search
      3. 11.4.3 Hill Climbing
      4. 11.4.4 The A/A* Algorithms
      5. 11.4.5 Problem Reduction
      6. 11.4.6 Means-ends Analysis
      7. 11.4.7 Mini-Max Search
      8. 11.4.8 Constraint Satisfaction
      9. 11.4.9 Measures of Search
    5. 11.5 Production Systems
    6. Chapter Summary
    7. Solved Problems
    8. Test Your Knowledge
    9. Answers
    10. Exercises
    11. Bibliography and Historical Notes
  18. Chapter 12: Advanced Search Strategies
    1. 12.1 Natural Evolution: A Brief Review
      1. 12.1.1 Chromosomes
      2. 12.1.2 Natural Selection
      3. 12.1.3 Crossover
      4. 12.1.4 Mutation
    2. 12.2 Genetic Algorithms (GAs)
      1. 12.2.1 Chromosomes
      2. 12.2.2 Fitness Function
      3. 12.2.3 Population
      4. 12.2.4 GA Operators
      5. 12.2.5 Elitism
      6. 12.2.6 GA Parameters
      7. 12.2.7 Convergence
    3. 12.3 Multi-objective Genetic Algorithms
      1. 12.3.1 MOO Problem Formulation
      2. 12.3.2 The Pareto-optimal Front
      3. 12.3.3 Pareto-optimal Ranking
      4. 12.3.4 Multi-objective Fitness
      5. 12.3.5 Multi-objective GA Process
    4. 12.4 Simulated Annealing
    5. Chapter Summary
    6. Solved Problems
    7. Test Your Knowledge
    8. Answers
    9. Exercises
    10. Bibliography and Historical Notes
  19. Chapter 13: Hybrid Systems
    1. 13.1 Neuro-genetic Systems
      1. 13.1.1 GA-based Weight Determination of Multi-layer Feed-forward Net
      2. 13.1.2 Neuro-evolution of Augmenting Topologies (NEAT)
    2. 13.2 Fuzzy-neural Systems
      1. 13.2.1 Fuzzy Neurons
      2. 13.2.2 Adaptive Neuro-fuzzy Inference System (ANFIS)
    3. 13.3 Fuzzy-genetic Systems
    4. Chapter Summary
    5. Test Your Knowledge
    6. Answers
    7. Bibliography and Historical Notes
  20. Acknowledgements
  21. Copyright
  22. Back Cover