Self-Organizing Maps

1. Front Matter

   Pages I-XVII

   PDF

2. Mathematical Preliminaries

   • Teuvo Kohonen

   Pages 1-58

3. Justification of Neural Modeling

   • Teuvo Kohonen

   Pages 59-83

4. The Basic SOM

   • Teuvo Kohonen

   Pages 85-144

5. Physiological Interpretation of SOM

   • Teuvo Kohonen

   Pages 145-155

6. Variants of SOM

   • Teuvo Kohonen

   Pages 157-201

7. Learning Vector Quantization

   • Teuvo Kohonen

   Pages 203-217

8. Applications

   • Teuvo Kohonen

   Pages 219-260

9. Hardware for SOM

   • Teuvo Kohonen

   Pages 261-276

10. An Overview of SOM Literature

    • Teuvo Kohonen

    Pages 277-301

11. Glossary of “Neural” Terms

    • Teuvo Kohonen

    Pages 303-331

12. Back Matter

    Pages 333-428

    PDF

The second, revised edition of this book was suggested by the impressive sales of the first edition. Fortunately this enabled us to incorporate new important results that had just been obtained. The ASSOM (Adaptive-Subspace SOM) is a new architecture in which invariant-feature detectors emerge in an unsupervised learning process. Its basic principle was already introduced in the first edition, but the motiva­ tion and theoretical discussion in the second edition is more thorough and consequent. New material has been added to Sect. 5.9 and this section has been rewritten totally. Correspondingly, Sect. 1.4, which deals with adaptive­ subspace classifiers in general and constitutes the prerequisite for the ASSOM principle, has also been extended and rewritten totally. Another new SOM development is the WEBSOM, a two-layer architecture intended for the organization of very large collections of full-text documents such as those found in the Internet and World Wide Web. This architecture was published after the first edition came out. The idea and results seemed to be so important that the new Sect. 7.8 has now been added to the second edition. Another addition that contains new results is Sect. 3.15, which describes the acceleration in the computing of very large SOMs. It was also felt that Chap. 7, which deals with 80M applications, had to be extended.

• Adaptive and Learning Networks
• Adaptive und Lernende Netze
• Cluster Analysis
• Klassifikator
• Klusteranalyse
• Neural Network
• Pattern Recognition
• Self-Organ
• algorithms
• classification
• neural modeling
• neural networks
• self-organizing map

"Rarely do books come along with an information density and value of content far above average. We now have another book in this category...a marvelous tool for finding just about any information that exists regarding self-organising maps. Rarely has any subject been provided with such an index of knowledge...Kohonen has created a masterpiece. I unhesitatingly recommend it." IEEE

• Neural Networks Research Centre, Helsinki University of Technology, Espoo, Finland

  Teuvo Kohonen

Policies and ethics