HybridSOM: A generic rule extraction framework for self-organizing feature maps

The self-organizing feature map (SOM) is an unsupervised neural network. It preserves a high-dimensional training data space's approximate characteristics, while scaling it to a two-dimensional grid. Few SOM-based rule extraction methods exist, and little analysis has been done on their overall viability. This paper presents the novel HybridSOMframework, which allows the combination of a SOM with any standard rule extraction algorithm, creating a customized hybrid rule extractor. Some HybridSOMvariations and traditional rule extraction algorithms are empirically compared, and the framework is critically discussed. This analysis also points to new conclusions on the viability of SOM-based rule extraction, in general.