Hierarchical overlapped SOM's for pattern classification

We develop a multilayer overlapped self-organizing maps (SOM's) with limited structure adaptation capabilities, and associated learning scheme for labeled pattern classification applications. The learning algorithm consists of the standard unsupervised SOM learning of synaptic weights as well as the supervised learning vector quantization (LVQ) 2 learning. As higher layer SOM's overlap, the final classification is made by fusing the classifications of top-level overlapped SOM's. We obtained the best results ever reported for any SOM-based numerals classification system.

[1]  Ralf Der,et al.  Hierarchical feature maps for non-linear component analysis , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[2]  E. Oja,et al.  Clustering Properties of Hierarchical Self-Organizing Maps , 1992 .

[3]  Gerald Sommer,et al.  Pattern Recognition by Self-Organizing Neural Networks , 1994 .

[4]  Sung-Bae Cho,et al.  Neural-network classifiers for recognizing totally unconstrained handwritten numerals , 1997, IEEE Trans. Neural Networks.

[5]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[6]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[7]  Hong Yan,et al.  Handwritten Digit Recognition Using Two-Layer Self-Organizing Maps , 1994, Int. J. Neural Syst..

[8]  Horst Bunke,et al.  Off-Line, Handwritten Numeral Recognition by Perturbation Method , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Daniel T. Long,et al.  Development of automatic target recognition for infrared sensor-based close-range land mine detector , 1995, Defense, Security, and Sensing.

[10]  Arthur Filippidis,et al.  Fuzzy Fusion for Surface Landmines Detection , 1997, ICONIP.

[11]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[12]  Thomas Villmann,et al.  Growing a hypercubical output space in a self-organizing feature map , 1997, IEEE Trans. Neural Networks.

[13]  Allen M. Peterson,et al.  Adaptive Vector Quantization Using a Self-Development Neural Network , 1990, IEEE J. Sel. Areas Commun..

[14]  Leslie S. Balfour,et al.  Polarization properties of targets and backgrounds in the infrared , 1993, Other Conferences.