This text presents neural network theory for diverse applications in a unified way, where the structure of artificial neural networks are characterized by distinguished classes of graphs. The book first provides a clear but concise exposition of neuroscience fundamentals, graph theory and alogorithms. It then moves to a detailed analysis of perceptron and lms-theory based neural networks, multilayer feedforward networks, and self-organizing competitive learning neural networks. The text culminates with a chapter on selected applications.

*"synopsis" may belong to another edition of this title.*

Published by
McGraw Hill Education
(1998)

ISBN 10: 0074635298
ISBN 13: 9780074635292

New
Softcover
First Edition
Quantity Available: > 20

Seller:

Rating

**Book Description **McGraw Hill Education, 1998. Softcover. Book Condition: New. First edition. This text presents neural network theory for diverse applications in a unified way, where the structure of artificial neural networks are characterized by distinguished classes of graphs. The book first provides a clear but concise exposition of neuroscience fundamentals, graph theory and alogorithms. It then moves to a detailed analysis of perceptron and lms-theory based neural networks, multilayer feedforward networks, and self-organizing competitive learning neural networks. The text culminates with a chapter on selected applications. Table of contents PART I: FUNDAMENTALS Chapter 1 Basics of Neuroscience and Artificial Neuron Models Chapter 2 Graphs Chapter 3 Algorithms PART II: FEEDFORWARD NETWORKS Chapter 4 Perceptions and LMS Algorithm Chapter 5 Multilayer Networks Chapter 6 Complexity of Learning Using Feedforward Networks Chapter 7 Adaptive Structure Networks PART III: RECURRENT NETWORKS Chapter 8 Symmetric and Asymmetric Recurrent Networks Chapter 9 Competitive Learning and Self-Organizing Networks PART IV: APPLICATIONS OF NEURAL NETWORKS Chapter 10 Neural Networks Approach to Solving Hard Problems Appendix A: Basis of Gradient-Based Optimization Methods Index Printed Pages: 484. Bookseller Inventory # 17450

More Information About This Seller | Ask Bookseller a Question

Published by
McGraw Hill Education
(1998)

ISBN 10: 0074635298
ISBN 13: 9780074635292

New
Softcover
First Edition
Quantity Available: > 20

Seller:

Rating

**Book Description **McGraw Hill Education, 1998. Softcover. Book Condition: New. First edition. This text presents neural network theory for diverse applications in a unified way, where the structure of artificial neural networks are characterized by distinguished classes of graphs. The book first provides a clear but concise exposition of neuroscience fundamentals, graph theory and alogorithms. It then moves to a detailed analysis of perceptron and lms-theory based neural networks, multilayer feedforward networks, and self-organizing competitive learning neural networks. The text culminates with a chapter on selected applications. Table of contents PART I: FUNDAMENTALS Chapter 1 Basics of Neuroscience and Artificial Neuron Models Chapter 2 Graphs Chapter 3 Algorithms PART II: FEEDFORWARD NETWORKS Chapter 4 Perceptions and LMS Algorithm Chapter 5 Multilayer Networks Chapter 6 Complexity of Learning Using Feedforward Networks Chapter 7 Adaptive Structure Networks PART III: RECURRENT NETWORKS Chapter 8 Symmetric and Asymmetric Recurrent Networks Chapter 9 Competitive Learning and Self-Organizing Networks PART IV: APPLICATIONS OF NEURAL NETWORKS Chapter 10 Neural Networks Approach to Solving Hard Problems Appendix A: Basis of Gradient-Based Optimization Methods Index Printed Pages: 484. Bookseller Inventory # 17450

More Information About This Seller | Ask Bookseller a Question