## Neural Networks: Algorithms and ApplicationsThis volume provides a comprehensive introduction to the use of neural networks in mechanical engineering applications. Beginning with an overview of different neural network topologies in the first two parts, functioning of human brain is also explained as an analogy with artificial models. Unsupervised models like Hopfield, Bi-directional Associative Memory, fuzzy Associative Memory, Adaptive Resonance Theory, kohonen as well as supervised architectures like Multi-Layer Perceptron, Counter Propagation networks and Radial Basis Function Networks are presented. The third part deals with applications of artificial neural networks for solving of design optimization problems, forward and inverse dynamic analysis applications and system identification and monitoring, as well as motion and vibration control in robotics and structural engineering. Software implementations for neural networks in C/C++ language and necessary optimization techniques in network training are given in Appendices. Key Features: Latest developments in standard neural network architectures like Fuzzy ARTMAP Network models such as Probabilistic and General Regression Neural Networks (GRNN) Carefully designed simulation examples Numerical Examples |

### What people are saying - Write a review

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

### Contents

Introduction | 3 |

Learning | 17 |

Hopfield Perceptron and related models | 35 |

Adaptive Resonance Theory | 66 |

SelfOrganization Maps | 82 |

Feedforward Back Propagation networks | 94 |

Hybrid Learning Neural Networks | 114 |

Probabilistic Models Fuzzy ARTMAP and Recurrent | 127 |

Application of neural networks | 157 |

Introduction to object oriented programming | 211 |

Optimization schemes used in neural networks | 221 |

Glossary | 233 |

### Common terms and phrases

applications approximation artificial neural networks ARTMAP associative memory backpropagation binary Boltzmann machine bottom-up calculated classification cluster competition layer competitive learning component computed connection weights constraints convergence corresponding defined delta rule desired output distance dynamic encoding Engg equation error example exemplars F2 layer feed-forward finite element model forward fuzzy set fuzzy-ART genetic algorithm given gradient descent GRNN Grossberg hidden layer hidden units Hopfield network IEEE Trans initial input layer input pattern input vector inverse iteration Kohonen learning algorithm learning law linear mapping method network model neurons nonlinear objective function optimization output layer output node output units output vector p-values perceptron predict probability problem processing element programming propagation RBF network recurrent neural networks response rule sample self-organizing sigmoid sigmoid function signal simulated annealing solution string structure synapses top-down tour unsupervised learning updated variables weight matrix weight vector zero