## Fundamentals of the New Artificial Intelligence: Neural, Evolutionary, Fuzzy and MoreThis book was originally titled “Fundamentals of the New Artificial Intelligence: Beyond Traditional Paradigms.” I have changed the subtitle to better represent the contents of the book. The basic philosophy of the original version has been kept in the new edition. That is, the book covers the most essential and widely employed material in each area, particularly the material important for real-world applications. Our goal is not to cover every latest progress in the fields, nor to discuss every detail of various techniques that have been developed. New sections/subsections added in this edition are: Simulated Annealing (Section 3.7), Boltzmann Machines (Section 3.8) and Extended Fuzzy if-then Rules Tables (Sub-section 5.5.3). Also, numerous changes and typographical corrections have been made throughout the manuscript. The Preface to the first edition follows. General scope of the book Artificial intelligence (AI) as a field has undergone rapid growth in diversification and practicality. For the past few decades, the repertoire of AI techniques has evolved and expanded. Scores of newer fields have been added to the traditional symbolic AI. Symbolic AI covers areas such as knowledge-based systems, logical reasoning, symbolic machine learning, search techniques, and natural language processing. The newer fields include neural networks, genetic algorithms or evolutionary computing, fuzzy systems, rough set theory, and chaotic systems. |

### What people are saying - Write a review

User Review - Flag as inappropriate

The chapters on neural network (Ist), fuuzy and chaos make it a good read.

### Contents

1 | |

3 | |

2 Neural Networks | 7 |

23 Basic Idea of the Backpropagation Model | 8 |

24 Details of the Backpropagation Model | 15 |

25 A Cookbook Recipe to Implement the Backpropagation Model | 22 |

26 Additional Technical Remarks on the Backpropagation Model | 24 |

27 Simple Perceptrons | 28 |

524 Operations Unique to Fuzzy Sets | 128 |

53 Fuzzy Relations | 130 |

532 Fuzzy Relations Defined on Ordinary Sets Fuzzy relations | 133 |

533 Fuzzy Relations Derived from Fuzzy Sets | 138 |

542 Fuzzy Logic Fundamentals | 139 |

55 Fuzzy Control | 143 |

Controlling Temperature with a Variable Heat Source | 150 |

553 Extended Fuzzy ifthen Rules Tables | 152 |

28 Applications of the Backpropagation Model | 31 |

29 General Remarks on Neural Networks | 33 |

Neural Networks Other Models | 37 |

32 Associative Memory | 40 |

33 Hopfield Networks | 41 |

The Basics | 46 |

342 TwoDimensional Layout | 48 |

Applications | 49 |

352 A General guideline to apply the HopfieldTank model to optimization problems | 54 |

353 Traveling Salesman Problem TSP | 55 |

36 The Kohonen Model | 58 |

37 Simulated Annealing | 63 |

38 Boltzmann Machines | 69 |

The Basics Architecture | 70 |

Algorithms | 76 |

384 Appendix Derivation of DeltaWeights | 81 |

Genetic Algorithms and Evolutionary Computing | 85 |

42 Fundamentals of Genetic Algorithms | 87 |

43 A Simple Illustration of Genetic Algorithms | 90 |

InputtoOutput Mapping | 95 |

the Traveling Salesman Problem TSP | 102 |

46 Schemata | 108 |

461 Changes of Schemata Over Generations | 109 |

462 Example of Schema Processing | 113 |

47 Genetic Programming | 116 |

48 Additional Remarks | 118 |

Fuzzy Systems | 121 |

52 Fundamentals of Fuzzy Sets | 123 |

522 Basic Fuzzy Set Relations | 125 |

523 Basic Fuzzy Set Operations and Their Properties | 126 |

554 A Note on Fuzzy Control Expert Systems | 155 |

56 Hybrid Systems | 156 |

57 Fundamental Issues | 157 |

58 Additional Remarks | 158 |

Rough Sets | 162 |

62 Review of Ordinary Sets and Relations | 165 |

63 Information Tables and Attributes | 167 |

64 Approximation Spaces | 170 |

65 Knowledge Representation Systems | 176 |

66 More on the Basics of Rough Sets | 180 |

67 Additional Remarks | 188 |

68 Case Study and Comparisons with Other Techniques | 191 |

681 Rough Sets Applied to the Case Study Case study process control | 192 |

682 ID3 Approach and the Case Study | 195 |

683 Comparisons with Other Techniques | 202 |

Chaos | 206 |

72 Representing Dynamical Systems | 210 |

722 Continuous dynamical systems | 212 |

73 State and Phase Spaces | 218 |

732 Cobwebs | 221 |

74 Equilibrium Solutions and Stability | 222 |

75 Attractors | 227 |

751 Fixedpoint attractors | 228 |

754 Chaotic attractors | 233 |

76 Bifurcations | 234 |

77 Fractals | 238 |

78 Applications of Chaos | 242 |

247 | |

### Other editions - View all

Fundamentals of the New Artificial Intelligence: Neural, Evolutionary, Fuzzy ... Toshinori Munakata No preview available - 2009 |

Fundamentals of the New Artificial Intelligence: Neural, Evolutionary, Fuzzy ... Toshinori Munakata No preview available - 2008 |

### Common terms and phrases

attractor backpropagation model Blood-P Boltzmann machine called cartesian product chaos chaotic systems characteristics condition attributes convergence decision attributes defined denoted determine discussed elements entropy equation equilibrium solution equivalence relation example exemplar patterns fractal fuzzy control fuzzy logic fuzzy relation fuzzy set fuzzy systems fuzzy variables genetic algorithms given Heart Problem Heart-Risk hidden neurons Hopfield network Hopfield-Tank initial condition input layer input patterns input vector iterations Kohonen machine learning mapping matrix membership function mutation n-queen problem neural network models nonlinear normal one-dimensional operations optimal solution ordinary sets output layer parameter partition induced perceptron perform phase space population positive programming random numbers randomly reduce representation represented rough set theory schema schemata Similarly simulated annealing specific steady-state solution Step string subset technique Temp temperature term trajectory two-dimensional types typically unsupervised learning values visible neurons weights xt+1