Ebook: Self-Organizing Maps

The Self-Organizing Map (SOM) algorithm was introduced by the author in 1981. Its theory and many applications form one of the major approaches to the contemporary artificial neural networks field, and new technolgies have already been based on it. The most important practical applications are in exploratory data analysis, pattern recognition, speech analysis, robotics, industrial and medical diagnostics, instrumentation, and control, and literally hundreds of other tasks. In this monograph the mathematical preliminaries, background, basic ideas, and implications are expounded in a clear, well-organized form, accessible without prior expert knowledge. Still the contents are handled with theoretical rigor.

---

The Self-Organizing Map (SOM) algorithm was introduced by the author in 1981. Its theory and many applications form one of the major approaches to the contemporary artificial neural networks field, and new technolgies have already been based on it. The most important practical applications are in exploratory data analysis, pattern recognition, speech analysis, robotics, industrial and medical diagnostics, instrumentation, and control, and literally hundreds of other tasks. In this monograph the mathematical preliminaries, background, basic ideas, and implications are expounded in a clear, well-organized form, accessible without prior expert knowledge. Still the contents are handled with theoretical rigor.
Content:
Front Matter....Pages I-XV
Mathematical Preliminaries....Pages 1-50
Justification of Neural Modeling....Pages 51-75
The Basic SOM....Pages 77-130
Physiological Interpretation of SOM....Pages 131-141
Variants of SOM....Pages 143-173
Learning Vector Quantization....Pages 175-189
Applications....Pages 191-213
Hardware for SOM....Pages 215-230
An Overview of SOM Literature....Pages 231-252
Glossary of “Neural” Terms....Pages 253-281
Back Matter....Pages 283-364

---

The Self-Organizing Map (SOM) algorithm was introduced by the author in 1981. Its theory and many applications form one of the major approaches to the contemporary artificial neural networks field, and new technolgies have already been based on it. The most important practical applications are in exploratory data analysis, pattern recognition, speech analysis, robotics, industrial and medical diagnostics, instrumentation, and control, and literally hundreds of other tasks. In this monograph the mathematical preliminaries, background, basic ideas, and implications are expounded in a clear, well-organized form, accessible without prior expert knowledge. Still the contents are handled with theoretical rigor.
Content:
Front Matter....Pages I-XV
Mathematical Preliminaries....Pages 1-50
Justification of Neural Modeling....Pages 51-75
The Basic SOM....Pages 77-130
Physiological Interpretation of SOM....Pages 131-141
Variants of SOM....Pages 143-173
Learning Vector Quantization....Pages 175-189
Applications....Pages 191-213
Hardware for SOM....Pages 215-230
An Overview of SOM Literature....Pages 231-252
Glossary of “Neural” Terms....Pages 253-281
Back Matter....Pages 283-364
....