상세정보

1.1 Overview We are living in a decade recently declared as the "Decade of the Brain". Neuroscientists may soon manage to work out a functional map of the brain, thanks to technologies that open windows on the mind. With the average human brain consisting of 15 billion neurons, roughly equal to the number of stars in our milky way, each receiving signals through as many as 10,000 synapses, it is quite a view. "The brain is the last and greatest biological frontier", says James Weston codiscoverer of DNA, considered to be the most complex piece of biological machinery on earth. After many years of research by neuroanatomists and neurophys­ iologists, the overall organization of the brain is well understood, but many of its detailed neural mechanisms remain to be decoded. In order to understand the functioning of the brain, neurobiologists have taken a bottom-up approach of studying the stimulus-response characteristics of single neurons and networks of neurons, while psy­ chologists have taken a top-down approach of studying brain func­ tions from the cognitive and behavioral level. While these two ap­ proaches are gradually converging, it is generally accepted that it may take another fifty years before we achieve a solid microscopic, intermediate, and macroscopic understanding of brain.

1.1 Overview We are living in a decade recently declared as the "Decade of the Brain". Neuroscientists may soon manage to work out a functional map of the brain, thanks to technologies that open windows on the mind. With the average human brain consisting of 15 billion neurons, roughly equal to the number of stars in our milky way, each receiving signals through as many as 10,000 synapses, it is quite a view. "The brain is the last and greatest biological frontier", says James Weston codiscoverer of DNA, considered to be the most complex piece of biological machinery on earth. After many years of research by neuroanatomists and neurophys­ iologists, the overall organization of the brain is well understood, but many of its detailed neural mechanisms remain to be decoded. In order to understand the functioning of the brain, neurobiologists have taken a bottom-up approach of studying the stimulus-response characteristics of single neurons and networks of neurons, while psy­ chologists have taken a top-down approach of studying brain func­ tions from the cognitive and behavioral level. While these two ap­ proaches are gradually converging, it is generally accepted that it may take another fifty years before we achieve a solid microscopic, intermediate, and macroscopic understanding of brain.

정보제공 :

CONTENTS
Acknowledgements = xiii
1 Introduction = 1
 1.1 Overview = 1
 1.2 Book Organization = 4
2 Neural Network Architectures and Learning Schemes = 9
 2.1 Introduction = 9
 2.2 Feed-forward Neural Networks = 11
 2.3 Feed-back Neural Networks = 46
 2.4 Self-organizing Neural Networks = 67
 2.5 Discussion = 75
 Appendix A2.1 = 76
 Appendix A2.2 = 77
 Appendix A2.3 = 79
 Appendix A2.4 = 82
 Appendix A2.5 = 84
3 ELEANNE: Efficient LEarning Algorithms for Neural NEtworks = 87
 3.1 Introduction = 87
 3.2 Recursive Least-squares Algorithms = 90
 3.3 Efficient Learning Algorithms for Single-layered Neural Networks = 98
 3.4 Efficient Learning Algorithms for Multi-layered Neural Networks = 109
 3.5 Computational Considerations = 121
 3.6 Experimental Results = 126
 3.7 Discussion = 131
 Appendix A3.1 = 132
 Appendix A3.2 = 134
 Appendix A3.3 = 135
 Appendix A3.4 = 138
4 Fast Learning Algorithms for Neural Networks = 141
 4.1 Introduction = 141
 4.2 A Generalized Training Criterion = 144
 4.3 Fast Learning Algorithms for Single-layered Neural Networks = 151
 4.4 Fast Learning Algorithms for Multi-layered Neural Networks = 161
 4.5 Exerimental Results = 176
 4.6 Discussion = 184
 Appendix A4.1 = 185
 Appendix A4.2 = 187
 Appendix A4.3 = 188
 Appendix A4.4 = 192
5 ALADIN: Algorithms for Learning and Architecture DetermINation = 195
 5.1 Introduction = 195
 5.2 Training Criteria = 198
 5.3 Neural Networks with one Hidden Layer = 199
 5.4 Neural Networks with Multiple Hidden Layers = 207
 5.5 Experimental Results = 209
 5.6 Discussion = 215
 Appendix A5.1 = 216
 Appendix A5.2 = 217
6 Performance Evaluation of Sigle-layered Neural Networks = 219
 6.1 Introduction = 219
 6.2 Optimal Least-squares Training of Single-layered Neural Networks = 220
 6.3 Capacity Considerations = 234
 6.4 Output Nonlinearities and Network Performance = 247
 6.5 Discussion = 249
 Appendix A6.1 = 250
 Appendix A6.2 = 251
 Appendix A6.3 = 254
 Appendix A6.4 = 256
7 High-order Neural Networks and Networks with Composite Key Patterns = 259
 7.1 Introduction = 259
 7.2 High-order Neural Networks = 260
 7.3 Neural Networks with Composite Key Patterns = 279
 7.4 Capacity Consederations = 287
 7.5 Discussion = 297
8 Applications of Neural Networks: A Case Study = 299
 8.1 Introduction = 299
 8.2 General Methodology for the Development of Neural Network Systems = 300
 8.3 Application of Neural Networks in Environmental Protection = 303
 8.4 Discussion = 315
9 Applications of Nerual Networks: A Review = 317
 9.1 Introduction = 317
 9.2 Optimization Problems = 319
 9.3 Image Compression = 330
 9.4 Recognition of Handwritten Signatures, Characters, and Digits = 338
 9.5 Text to Speech Conversion = 347
 9.6 Classification Applications = 349
 9.7 Medical Diagnosis = 351
 9.8 Prediction of Secondary Structures of Proteins = 354
 9.9 Weather Forecasting = 358
 9.10 Financial Predictions = 360
 9.11 Other Applications = 368
10 Future Treans and Directions = 371
References = 375
Subject Index = 413
Author Index = 435