Self-Organizing Maps

1. Front Matter

   Pages I-XV

   PDF

2. Mathematical Preliminaries

   • Teuvo Kohonen

   Pages 1-50

3. Justification of Neural Modeling

   • Teuvo Kohonen

   Pages 51-75

4. The Basic SOM

   • Teuvo Kohonen

   Pages 77-130

5. Physiological Interpretation of SOM

   • Teuvo Kohonen

   Pages 131-141

6. Variants of SOM

   • Teuvo Kohonen

   Pages 143-173

7. Learning Vector Quantization

   • Teuvo Kohonen

   Pages 175-189

8. Applications

   • Teuvo Kohonen

   Pages 191-213

9. Hardware for SOM

   • Teuvo Kohonen

   Pages 215-230

10. An Overview of SOM Literature

    • Teuvo Kohonen

    Pages 231-252

11. Glossary of “Neural” Terms

    • Teuvo Kohonen

    Pages 253-281

12. Back Matter

    Pages 283-364

    PDF

The book we have at hand is the fourth monograph I wrote for Springer­ Verlag. The previous one named "Self-Organization and Associative Mem­ ory" (Springer Series in Information Sciences, Volume 8) came out in 1984. Since then the self-organizing neural-network algorithms called SOM and LVQ have become very popular, as can be seen from the many works re­ viewed in Chap. 9. The new results obtained in the past ten years or so have warranted a new monograph. Over these years I have also answered lots of questions; they have influenced the contents of the present book. I hope it would be of some interest and help to the readers if I now first very briefly describe the various phases that led to my present SOM research, and the reasons underlying each new step. I became interested in neural networks around 1960, but could not in­ terrupt my graduate studies in physics. After I was appointed Professor of Electronics in 1965, it still took some years to organize teaching at the uni­ versity. In 1968 - 69 I was on leave at the University of Washington, and D. Gabor had just published his convolution-correlation model of autoasso­ ciative memory. I noticed immediately that there was something not quite right about it: the capacity was very poor and the inherent noise and crosstalk were intolerable. In 1970 I therefore sugge~ted the auto associative correlation matrix memory model, at the same time as J.A. Anderson and K. Nakano.

• Mathematica
• algorithms
• artificial neural network
• calculus
• classification
• data analysis
• filters
• nervous system
• neural modeling
• neural networks
• pattern recognition
• self-organizing map
• signal processing
• telecommunications
• unsupervised learning

• Laboratory of Computer and Information Science, Helsinki University of Technology, Espoo 15, Finland

  Teuvo Kohonen

Policies and ethics