Ebook: Neural Networks: A Systematic Introduction

Artificial neural networks are an alternative computational paradigm with roots in neurobiology which has attracted increasing interest in recent years. This book is a comprehensive introduction to the topic that stresses the systematic development of the underlying theory. Starting from simple threshold elements, more advanced topics are introduced, such as multilayer networks, efficient learning methods, recurrent networks, and self-organization. The various branches of neural network theory are interrelated closely and quite often unexpectedly, so the chapters treat the underlying connection between neural models and offer a unified view of the current state of research in the field.
The book has been written for anyone interested in understanding artificial neural networks or in learning more about them. The only mathematical tools needed are those learned during the first two years at university. The text contains more than 300 figures to stimulate the intuition of the reader and to illustrate the kinds of computation performed by neural networks. Material from the book has been used successfully for courses in Germany, Austria and the United States.

---

Artificial neural networks are an alternative computational paradigm with roots in neurobiology which has attracted increasing interest in recent years. This book is a comprehensive introduction to the topic that stresses the systematic development of the underlying theory. Starting from simple threshold elements, more advanced topics are introduced, such as multilayer networks, efficient learning methods, recurrent networks, and self-organization. The various branches of neural network theory are interrelated closely and quite often unexpectedly, so the chapters treat the underlying connection between neural models and offer a unified view of the current state of research in the field.
The book has been written for anyone interested in understanding artificial neural networks or in learning more about them. The only mathematical tools needed are those learned during the first two years at university. The text contains more than 300 figures to stimulate the intuition of the reader and to illustrate the kinds of computation performed by neural networks. Material from the book has been used successfully for courses in Germany, Austria and the United States.

---

Artificial neural networks are an alternative computational paradigm with roots in neurobiology which has attracted increasing interest in recent years. This book is a comprehensive introduction to the topic that stresses the systematic development of the underlying theory. Starting from simple threshold elements, more advanced topics are introduced, such as multilayer networks, efficient learning methods, recurrent networks, and self-organization. The various branches of neural network theory are interrelated closely and quite often unexpectedly, so the chapters treat the underlying connection between neural models and offer a unified view of the current state of research in the field.
The book has been written for anyone interested in understanding artificial neural networks or in learning more about them. The only mathematical tools needed are those learned during the first two years at university. The text contains more than 300 figures to stimulate the intuition of the reader and to illustrate the kinds of computation performed by neural networks. Material from the book has been used successfully for courses in Germany, Austria and the United States.
Content:
Front Matter....Pages I-XX
The Biological Paradigm....Pages 3-27
Threshold Logic....Pages 29-53
Weighted Networks—The Perceptron....Pages 55-76
Perceptron Learning....Pages 77-98
Unsupervised Learning and Clustering Algorithms....Pages 99-121
One and Two Layered Networks....Pages 123-148
The Backpropagation Algorithm....Pages 149-182
Fast Learning Algorithms....Pages 183-225
Statistics and Neural Networks....Pages 227-261
The Complexity of Learning....Pages 263-285
Fuzzy Logic....Pages 287-308
Associative Networks....Pages 309-334
The Hopfield Model....Pages 335-369
Stochastic Networks....Pages 371-387
Kohonen Networks....Pages 389-410
Modular Neural Networks....Pages 411-425
Genetic Algorithms....Pages 427-448
Hardware for Neural Networks....Pages 449-476
Back Matter....Pages 477-502

---

Artificial neural networks are an alternative computational paradigm with roots in neurobiology which has attracted increasing interest in recent years. This book is a comprehensive introduction to the topic that stresses the systematic development of the underlying theory. Starting from simple threshold elements, more advanced topics are introduced, such as multilayer networks, efficient learning methods, recurrent networks, and self-organization. The various branches of neural network theory are interrelated closely and quite often unexpectedly, so the chapters treat the underlying connection between neural models and offer a unified view of the current state of research in the field.
The book has been written for anyone interested in understanding artificial neural networks or in learning more about them. The only mathematical tools needed are those learned during the first two years at university. The text contains more than 300 figures to stimulate the intuition of the reader and to illustrate the kinds of computation performed by neural networks. Material from the book has been used successfully for courses in Germany, Austria and the United States.
Content:
Front Matter....Pages I-XX
The Biological Paradigm....Pages 3-27
Threshold Logic....Pages 29-53
Weighted Networks—The Perceptron....Pages 55-76
Perceptron Learning....Pages 77-98
Unsupervised Learning and Clustering Algorithms....Pages 99-121
One and Two Layered Networks....Pages 123-148
The Backpropagation Algorithm....Pages 149-182
Fast Learning Algorithms....Pages 183-225
Statistics and Neural Networks....Pages 227-261
The Complexity of Learning....Pages 263-285
Fuzzy Logic....Pages 287-308
Associative Networks....Pages 309-334
The Hopfield Model....Pages 335-369
Stochastic Networks....Pages 371-387
Kohonen Networks....Pages 389-410
Modular Neural Networks....Pages 411-425
Genetic Algorithms....Pages 427-448
Hardware for Neural Networks....Pages 449-476
Back Matter....Pages 477-502
....