A Kohonen Network is a selforganizing neural network trained by an unsupervised learning algorithm. It can be used to classify a set of input vectors according to their similarity. The output of such a network is usually a twodimensional map, thus, the Kohonen Network is a method for projecting objects from a multidimensional space into a twodimensional space. This projection keeps the topology of the multidimensional space, i.e., points which are near to one another in the multidimensional space are neighbors in the twodimensional space as well. An advantage of this method is that the results of such a mapping can easily be visualized.

A Kohonen Network has a cubic structure; it has a twodimensional arrangement of neurons, each having m weights. If the input for the network is a set of mdimensional vectors the network’s architecture is n x l x m dimensional. The network adapts its values with respect to the input values and thus reflects the input data. This approach is unsupervised learning as the adaptation is merely done with respect to the data describing the individual objects. 