Kullback-Leibler Divergence minimization for competitive learning of self-organizing maps

In this paper, we employ the Kullback-Leibler Divergence (KD) measure from information theory within the framework of Self Organizing Maps applied to network planning and dimensioning. Here, the KD measure estimates the closeness among probability densities (or relative Entropy), and is used instead of the distance or dot product measures. Applied to a real network planning under the supervision of link budget calculations, the new method shows improved performance and a promise of wider network applications.