## Analysis and Applications of Artificial Neural NetworksThorough, compact, and self-contained, this explanation and analysis of a broad range of neural nets is conveniently structured so that readers can first gain a quick global understanding of neural nets -- without the mathematics -- and can then delve into mathematical specifics as necessary. The behavior of neural nets is first explained from an intuitive perspective; the formal analysis is then presented; and the practical implications of the formal analysis are stated separately. Analyzes the behavior of the six main types of neural networks -- The Binary Perceptron, The Continuous Perceptron (Multi-Layer Perceptron), The Bidirectional Memories, The Hopfield Network (Associative Neural Nets), The Self-Organizing Neural Network of Kohonen, and the new Time Sequentional Neural Network. For technically-oriented individuals working with information retrieval, pattern recognition, speech recognition, signal processing, data classification. |

### What people are saying - Write a review

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

### Contents

Introduction | 1 |

The continuous multilayer Perceptron | 66 |

of a sine wave | 158 |

Copyright | |

2 other sections not shown

### Common terms and phrases

adaptive recruitment learning approximate argument arithmetical conjunctive normal artificial neural networks artificial neuron behaviour Boolean function classification problem components conjunctive normal form corresponding counterexamples data points data set defined distance duration equal error function first-layer neurons frequency function realized given in Figure gradient descent initial weights learning phase learning process learning set learning steps linear threshold function logical function method minimizing neighbouring neurons neural lattice neural net algorithm number of neurons observation vectors optimal output neuron pattern phoneme pixel Practical statement receptive fields recruitment learning rule reinforcement learning reinforcement learning rule represented samples second layer self-organizing algorithm self-organizing neural network separating hyperplane sequence sigmoid functions sigmoid transfer function sine wave single-neuron binary Perceptron single-neuron Perceptron subset SWCs synaptic Table target value Theorem threshold labelling topology preservation training set transfer function two-layer Perceptron unknown function vector quantization vector ws weight vector weighted input window winning neuron zero

### References to this book

Invented Here: Maximizing Your Organization's Internal Growth and Profitability Bart Victor,Andrew C. Boynton No preview available - 1998 |

The Lies About Money: Achieving Financial Security and True Wealth by ... Ric Edelman Limited preview - 2007 |