Kohonen Neural Networks — The Classifiers

A type of neural network that has been proved to be successful in a series of applications is based on self-organizing maps (SOMs) or Kohonen neural networks [61]. Whereas most of the networks are designed for supervised learning tasks (i.e., the relationship between input and output must be known in form of a mathematical model), Kohonen neural networks are designed primarily for unsupervised learning where no prior knowledge about this relationship is necessary [62,63]. 

FIGURE 4.13 A Kohonen network in three dimensions is a combination of neuron vectors, in which the number of components n matches the ones in the input vector v. The weights w in the Kohonen network are adapted during training. The most similar neuron is determined by the Euclidean distance the resulting neuron is the central neuron, from which the adaptation of the network weights starts. 

The weights of the central neuron are then adjusted to the weights of the input vectors. The amount of adjustment of neurons surrounding the central neuron is actually determined by their topological distance. The neuron weights are corrected by 

Kohonen networks can be arranged in toroidal shape that is, both ends of each plane are connected to each other so that the complete map forms a torns. Conse-qnently, each neuron has the same number of neighbors, and a central nenron at the edge of the plane influences neurons at the other end of plane (Fignre 4.14). 

---