## Fuzzy Logic and Neural Network HandbookFuzzy logic and neural networks, which are linked, have emerged as the keystone of developing intelligent computer systems with broad application throughout engineering and science. Neural nets allow them to better manage uncertainty. That combination gives the ability to solve many classes of problems more efficiently. This book deals with principles and algorithms, applications and architectures and systems. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

Learning Categorization Rule Formation and Prediction | 1-3 |

JeanPaul Haton Universite Henri Poincare CRININRIANancy France chap | 1-14 |

Reactive Control Using Fuzzy Logic Enrique H Ruspini 24 1 | 1-24 |

Copyright | |

57 other sections not shown

### Common terms and phrases

activation function adaptive algorithm annealing neural network application approach approximate reasoning architecture backpropagation basis functions centroidal clustering computational constraint path convergence convex data set defined defuzzification degree of membership density deterministic annealing neural dynamic error estimate example FAMM feedforward FIGURE FMFs Fuzzy ARTMAP fuzzy classifier fuzzy logic fuzzy relational equation fuzzy rules fuzzy sets fuzzy system gaussian Grossberg hidden layer hidden neurons hyperplanes IEEE IEEE Transactions if-part input space input variables iteration learning license plate recognition linear mapping matrix membership functions method minimal mutual information neural models neurons nodes nonlinear operator optimization problems output parameter pattern recognition percent performance possible worlds prediction probabilistic probability programming recognition rate recurrent neural networks regression samples shown in Fig solution sonar statistical supervised learning techniques test data then-part set theorem tion training data units walk function weights