Use of the Fuzzy Self-Organizing Map in pattern recognition

Kohonen's self-organizing map is one of the best-known neural network models. In previous work, we developed a fuzzy version of the model called: Fuzzy Self-Organizing Map (T. Kohonen, 1988). The new version is similar to the fuzzy logic controllers, and thus it is easy to use and computationally efficient. On the other hand, since the Fuzzy Self-Organizing Map is derived from the original model, the Kohonen learning laws can be used to tune the system. We show how the Fuzzy Self-Organizing Map can be used in pattern recognition. For this purpose, we introduce a new multiple input, multiple output version of the Fuzzy Self-Organizing Map.<<ETX>>

[1]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[2]  James C. Bezdek,et al.  Fuzzy Kohonen clustering networks , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[3]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[4]  Petri Vuorimaa,et al.  Fuzzy self-organizing map , 1994 .

[5]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[6]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[7]  Teuvo Kohonen,et al.  Improved versions of learning vector quantization , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[8]  H. R. Berenji,et al.  Fuzzy Logic Controllers , 1992 .