Computational Intelligence

Computational Intelligence

by Russell C. Eberhart, Yuhui Shi
Released April 2011
Publisher(s): Morgan Kaufmann
ISBN: 9780080553832

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Computational Intelligence: Concepts to Implementations provides the most complete and practical coverage of computational intelligence tools and techniques to date. This book integrates various natural and engineering disciplines to establish Computational Intelligence. This is the first comprehensive textbook on the subject, supported with lots of practical examples. It asserts that computational intelligence rests on a foundation of evolutionary computation. This refreshing view has set the book apart from other books on computational intelligence.

This book lays emphasis on practical applications and computational tools, which are very useful and important for further development of the computational intelligence field. Focusing on evolutionary computation, neural networks, and fuzzy logic, the authors have constructed an approach to thinking about and working with computational intelligence that has, in their extensive experience, proved highly effective. The book moves clearly and efficiently from concepts and paradigms to algorithms and implementation techniques by focusing, in the early chapters, on the specific con. It explores a number of key themes, including self-organization, complex adaptive systems, and emergent computation. It details the metrics and analytical tools needed to assess the performance of computational intelligence tools. The book concludes with a series of case studies that illustrate a wide range of successful applications.

This book will appeal to professional and academic researchers in computational intelligence applications, tool development, and systems.

  • Moves clearly and efficiently from concepts and paradigms to algorithms and implementation techniques by focusing, in the early chapters, on the specific concepts and paradigms that inform the authors' methodologies
  • Explores a number of key themes, including self-organization, complex adaptive systems, and emergent computation
  • Details the metrics and analytical tools needed to assess the performance of computational intelligence tools
  • Concludes with a series of case studies that illustrate a wide range of successful applications
  • Presents code examples in C and C++
  • Provides, at the end of each chapter, review questions and exercises suitable for graduate students, as well as researchers and practitioners engaged in self-study

Table of contents

  1. Front Cover
  2. Computational Intelligence
  3. Copyright Page
  4. Table of Contents (1/2)
  5. Table of Contents (2/2)
  6. Preface (1/2)
  7. Preface (2/2)
  8. Chapter 1. Foundations
    1. Definitions
    2. Biological Basis for Neural Networks
    3. Behavioral Motivations for Fuzzy Logic
    4. Myths about Computational Intelligence
    5. Computational Intelligence Application Areas
    6. Summary
    7. Exercises
  9. Chapter 2. Computational Intelligence
    1. Adaptation (1/2)
    2. Adaptation (2/2)
    3. Self-organization and Evolution
    4. Historical Views of Computational Intelligence
    5. Computational Intelligence as Adaptation and Self-organization
    6. The Ability to Generalize
    7. Computational Intelligence and Soft Computing versus Artificial Intelligence and Hard Computing
    8. Summary
    9. Exercises
  10. Chapter 3. Evolutionary Computation Concepts and Paradigms
    1. History of Evolutionary Computation (1/2)
    2. History of Evolutionary Computation (2/2)
    3. Evolutionary Computation Overview
    4. Genetic Algorithms (1/4)
    5. Genetic Algorithms (2/4)
    6. Genetic Algorithms (3/4)
    7. Genetic Algorithms (4/4)
    8. Evolutionary Programming (1/2)
    9. Evolutionary Programming (2/2)
    10. Evolution Strategies (1/2)
    11. Evolution Strategies (2/2)
    12. Genetic Programming (1/2)
    13. Genetic Programming (2/2)
    14. Particle Swarm Optimization
    15. Summary
    16. Exercises
  11. Chapter 4. Evolutionary Computation Implementations
    1. Implementation Issues (1/2)
    2. Implementation Issues (2/2)
    3. Genetic Algorithm Implementation (1/3)
    4. Genetic Algorithm Implementation (2/3)
    5. Genetic Algorithm Implementation (3/3)
    6. Particle Swarm Optimization Implementation (1/5)
    7. Particle Swarm Optimization Implementation (2/5)
    8. Particle Swarm Optimization Implementation (3/5)
    9. Particle Swarm Optimization Implementation (4/5)
    10. Particle Swarm Optimization Implementation (5/5)
    11. Summary
    12. Exercises
  12. Chapter 5. Neural Network Concepts and Paradigms
    1. Neural Network History (1/4)
    2. Neural Network History (2/4)
    3. Neural Network History (3/4)
    4. Neural Network History (4/4)
    5. What Neural Networks are and Why They are Useful
    6. Neural Network Components and Terminology (1/2)
    7. Neural Network Components and Terminology (2/2)
    8. Neural Network Topologies
    9. Neural Network Adaptation (1/2)
    10. Neural Network Adaptation (2/2)
    11. Comparing Neural Networks and Other Information Processing Methods
    12. Preprocessing
    13. Postprocessing
    14. Summary
    15. Exercises
  13. Chapter 6. Neural Network Implementations
    1. Implementation Issues (1/4)
    2. Implementation Issues (2/4)
    3. Implementation Issues (3/4)
    4. Implementation Issues (4/4)
    5. Back-propagation Implementation (1/4)
    6. Back-propagation Implementation (2/4)
    7. Back-propagation Implementation (3/4)
    8. Back-propagation Implementation (4/4)
    9. The Kohonen Network Implementations (1/6)
    10. The Kohonen Network Implementations (2/6)
    11. The Kohonen Network Implementations (3/6)
    12. The Kohonen Network Implementations (4/6)
    13. The Kohonen Network Implementations (5/6)
    14. The Kohonen Network Implementations (6/6)
    15. Evolutionary Back-propagation Network Implementation
    16. Summary
    17. Exercises
  14. Chapter 7. Fuzzy Systems Conceptsand Paradigms
    1. History
    2. Fuzzy Sets and Fuzzy Logic
    3. The Theory of Fuzzy Sets (1/2)
    4. The Theory of Fuzzy Sets (2/2)
    5. Approximate Reasoning (1/4)
    6. Approximate Reasoning (2/4)
    7. Approximate Reasoning (3/4)
    8. Approximate Reasoning (4/4)
    9. Developing a Fuzzy Controller (1/3)
    10. Developing a Fuzzy Controller (2/3)
    11. Developing a Fuzzy Controller (3/3)
    12. Summary
    13. Exercises
  15. Chapter 8. Fuzzy Systems Implementations
    1. Implementation Issues
    2. Fuzzy Rule System Implementation (1/7)
    3. Fuzzy Rule System Implementation (2/7)
    4. Fuzzy Rule System Implementation (3/7)
    5. Fuzzy Rule System Implementation (4/7)
    6. Fuzzy Rule System Implementation (5/7)
    7. Fuzzy Rule System Implementation (6/7)
    8. Fuzzy Rule System Implementation (7/7)
    9. Evolving Fuzzy Rule Systems (1/4)
    10. Evolving Fuzzy Rule Systems (2/4)
    11. Evolving Fuzzy Rule Systems (3/4)
    12. Evolving Fuzzy Rule Systems (4/4)
    13. Summary
    14. Exercises
  16. Chapter 9. Computational Intelligence Implementations
    1. Implementation Issues
    2. Fuzzy Evolutionary Fuzzy Rule System Implementation
    3. Choosing the Best Tools
    4. Applying Computational Intelligence to Data Mining
    5. Summary
    6. Exercises
  17. Chapter 10. Performance Metrics
    1. General Issues
    2. Percent Correct
    3. Average Sum-squared Error
    4. Absolute Error
    5. Normalized Error
    6. Evolutionary Algorithm Effectiveness Metrics
    7. Mann–Whitney U Test
    8. Receiver Operating Characteristic Curves
    9. Recall and Precision
    10. Other ROC-related Measures
    11. Confusion Matrices
    12. Chi-square Test
    13. Summary
    14. Exercises
  18. Chapter 11. Analysis and Explanation
    1. Sensitivity Analysis
    2. Hinton Diagrams
    3. Computational Intelligence Tools for Explanation Facilities (1/2)
    4. Computational Intelligence Tools for Explanation Facilities (2/2)
    5. Summary
    6. Exercises
  19. Bibliography (1/4)
  20. Bibliography (2/4)
  21. Bibliography (3/4)
  22. Bibliography (4/4)
  23. Index (1/3)
  24. Index (2/3)
  25. Index (3/3)
  26. About the Authors
  27. Chapter 12. Case Study Summaries
    1. Case Study Preview
    2. Case Study 1: Detection of Electroencephalogram Spikes (1/2)
    3. Case Study 1: Detection of Electroencephalogram Spikes (2/2)
    4. Case Study 2: Determining Battery State of Charge
    5. Case Study 3: Schedule Optimization (1/4)
    6. Case Study 3: Schedule Optimization (2/4)
    7. Case Study 3: Schedule Optimization (3/4)
    8. Case Study 3: Schedule Optimization (4/4)
    9. Case Study 4: Control System Design (1/2)
    10. Case Study 4: Control System Design (2/2)
  28. Summary
  29. Exercises
  30. Glossary (1/3)
  31. Glossary (2/3)
  32. Glossary (3/3)

Product information

  • Title: Computational Intelligence
  • Author(s): Russell C. Eberhart, Yuhui Shi
  • Release date: April 2011
  • Publisher(s): Morgan Kaufmann
  • ISBN: 9780080553832