Enhanced descriptions from Syndetics:

Neural Networks, Second Edition provides a complete introduction to neural networks. It describes what they are, what they can do, and how they do it. While some scientific background is assumed, the reader is not expected to have any prior knowledge of neural networks. These networks are explained and discussed by means of examples, so that by the end of the book the reader will have a good overall knowledge of developments right up to current work in the field.

- Updated and expanded second edition
- Main networks covered are: feedforward networks such as the multilayered perceptron, Boolean networks such as the WISARD, feedback networks such as the Hopfield network, statistical networks such as the Boltzmann machine and Radial-Basis function networks, and self-organising networks such as Kohonen's self-organizing maps. Other networks are referred to throughout the text to give historical interest and alternative architectures
- The applications discussed will appeal to student engineers and computer scientists interested in character recognition, intelligent control and threshold logic. The final chapter looks at ways of implementing a neural network, including electronic and optical systems

This book is suitable for undergraduates from Computer Science and Electrical Engineering Courses who are taking a one module course on neural networks, and for researchers and computer science professionals who need a quick introduction to the subject.

PHIL PICTON is Professor of Intelligent Computer Systems at University College Northampton. Prior to this he was a lecturer at the Open University where he contributed to distance learning courses on control engineering, electronics, mechatronics and artificial intelligence. His research interests include pattern recognition, intelligent control and logic design.

Table of contents provided by Syndetics

• Preface (p. ix)
• Neural networks as part of artificial intelligence (p. ix)
• Recent developments in neural networks (p. x)
• Overview of the book (p. xi)
• Chapter 1 Introduction (p. 1)
• Chapter overview (p. 1)
• 1.1 What is a neural network? (p. 1)
• 1.2 Pattern classification (p. 1)
• 1.3 Learning and generalisation (p. 4)
• 1.4 The structure of neural networks (p. 5)
• Chapter summary (p. 12)
• Self-test questions (p. 12)
• Self-test answers (p. 13)
• Chapter 2 Adaline (p. 15)
• Chapter overview (p. 15)
• 2.1 Training and weight adjustment (p. 15)
• 2.2 The delta rule (p. 19)
• 2.3 Input and output values (p. 23)
• Chapter summary (p. 24)
• Self-test questions (p. 24)
• Self-test answers (p. 26)
• Chapter 3 Perceptrons (p. 29)
• Chapter overview (p. 29)
• 3.1 Single layer perceptrons (p. 29)
• 3.2 Linear separability (p. 32)
• 3.3 Back-propagation (p. 37)
• 3.4 Variations on the standard multi-layered perceptron (p. 44)
• 3.5 Stopping training (p. 45)
• Chapter summary (p. 46)
• Self-test questions (p. 47)
• Self-test answers (p. 48)
• Chapter 4 Boolean neural networks (p. 50)
• Chapter overview (p. 50)
• 4.1 Bledsoe and Browning's program (p. 50)
• 4.2 WISARD (p. 53)
• 4.3 The arguments in favour of random connections (p. 56)
• 4.4 Other work (p. 59)
• Chapter summary (p. 63)
• Self-test questions (p. 63)
• Self-test answers (p. 64)
• Chapter 5 Associative memory and feedback networks (p. 66)
• Chapter overview (p. 66)
• 5.1 Associative memory (p. 66)
• 5.2 The learning matrix (p. 68)
• 5.3 The Hopfield network (p. 71)
• 5.4 Energy (p. 78)
• 5.5 The Hamming network (p. 80)
• 5.6 Bidirectional associative memory (BAM) (p. 82)
• Chapter summary (p. 85)
• Self-test questions (p. 85)
• Self-test answers (p. 86)
• Chapter 6 Statistical neural networks (p. 91)
• Chapter overview (p. 91)
• 6.1 Introduction (p. 91)
• 6.2 Boltzmann machine (p. 91)
• 6.3 Cauchy machine (p. 99)
• 6.4 PLN (p. 100)
• 6.5 Radial basis function networks (p. 102)
• 6.6 Probabilistic neural network (PNN) (p. 106)
• 6.7 General regression neural network (GRNN) (p. 109)
• Chapter summary (p. 111)
• Self-test questions (p. 111)
• Self-test answers (p. 112)
• Chapter 7 Self-organising networks (p. 115)
• Chapter overview (p. 115)
• 7.1 Introduction (p. 115)
• 7.2 Instar and outstar networks (p. 116)
• 7.3 Adaptive resonance theorem (ART) (p. 121)
• 7.4 Kohonen networks (p. 126)
• 7.5 Neocognitron (p. 129)
• Chapter summary (p. 132)
• Self-test questions (p. 133)
• Self-test answers (p. 134)
• Chapter 8 Neural networks in control engineering (p. 137)
• Chapter overview (p. 137)
• 8.1 Introduction (p. 137)
• 8.2 Michie's boxes (p. 138)
• 8.3 Reinforcement learning (p. 140)
• 8.4 ADALINE (p. 143)
• 8.5 Multi-layered perceptron (p. 145)
• 8.6 Recurrent neural networks (p. 147)
• 8.7 The Kohonen network (p. 150)
• 8.8 Neuro-fuzzy systems (p. 151)
• Chapter summary (p. 152)
• Self-test questions (p. 152)
• Self-test answers (p. 153)
• Chapter 9 Threshold logic (p. 155)
• Chapter overview (p. 155)
• 9.1 Introduction (p. 155)
• 9.2 A test for linear separability (p. 156)
• 9.3 Classification of logic functions (p. 159)
• 9.4 Multi-threshold logic functions (p. 162)
• Chapter summary (p. 163)
• Self-test questions (p. 164)
• Self-test answers (p. 165)
• Chapter 10 Implementation (p. 167)
• Chapter overview (p. 167)
• 10.1 Introduction (p. 167)
• 10.2 Electronic neural networks (p. 168)
• 10.3 Optical neural networks (p. 175)
• 10.4 Molecular systems (p. 180)
• Chapter summary (p. 180)
• Self-test answers (p. 180)
• Self-test questions (p. 180)
• Conclusions (p. 182)
• Appendix A Derivation of the delta rule (p. 184)
• References (p. 189)
• Index

Author notes provided by Syndetics