Neural networks algorithms, applications, and programming techniques James A. Freeman and David M. Skapura

Include bibliography

Chapter 1
Introduction to ANS Technology
1.1 Elementary Neurophysiology 22
From Neurons to ANS 31
ANS Simulation 44
Chapter 2 .
Adallne and Madaline 59
2.1 Review of Signal Processing 59
Adaline and the Adaptive Linear Combiner 69
Applications of Adaptive Signal Processing 82
The Madaline 86
Simulating the Adaline 93
Chapter 3
Backpropagatlon 103
3.1 The Backpropagation Network 103
The Generalized Delta Rule 107
Practical Considerations 117
BPN Applications 120
The Backpropagation Simulator 128
Chapter 4
The BAM and the Hopfield Memory 141
4.1 Associative-Memory Definitions 142 ' ; (Moqn
4.2 The BAM 145 i ft.wwo .
4.3 The Hopfield Memory 155
4.4 Simulating the BAM 170
Chapter 5
Simulated Annealing 183
5.1 Information Theory and Statistical Mechanics 185
5.2 The Boltzmann Machine 193
5.3 The Boltzmann Simulator 203
5.4 Using the Boitzmann Simulator 221
Chapter 6
The Counterpropagation Network 227
6.1 CPN Building Blocks 229
6.2 CPN Data Processing 249
6.3 An Image-Classification Example 258
6.4 The CPN Simulator 261
Chapter 7
Self-Organizing Maps 277
7.1 SOM Data Processing 279
7.2 Applications of Self-Organizing Maps 288
7.3 Simulating the SOM 293
Chapter 8
Adaptive Resonance Theory 305
8.1 ART Network Description 307
8.2 ART1 312 _ ,
8.3 ART2 330 _ uyio
8.4 The ART1 Simulator 341 .
8.5 ART2 Simulation 350
Chapter 9
Spatiotemporal Pattern Classification 355
9.1 The Formal Avalanche 356
9.2 Architectures of Spatiotemporal Networks (STNS) 359
9.3 The Sequential Competitive Avalanche Field 369
9.4 Applications of STNS 377
9.5 StN Simulation 378
Chapter TO
The Neocognitron 387
10.1 Neocognitron Architecture 390
10.2 Neocognitron Data Processing 395
10.3 Performance of the Neocognitron 403
10.4 Addition of Lateral Inhibition and Feedback to the
Neocognitron 404