Preprocessing phase for initializing the PRSOM architecture

The self-organizing map (SOM) is a popular neural network which was designed for solving problems that involve tasks such as clustering and visualization. Specially, It provides a new strategy of clustering using a competition and co-operation principal. The probabilistic Kohonen network (PRSOM) is the stochastic version of classical one. However, determination of the optimal number of neurons and their initial weight vectors in the map is still a big problem in the literature. These parameters have a great impact on the learning process of the network, the convergence and the quality of results. Also determination of clusters´ number of datasets is a very difficult task. In this paper we extend the original Kohonen network to classify unlabeled data and determine the number of clusters. The task consists of generating a heuristic method before the learning phase of the network. The main goal of this method is looking for the initial parameters of the map. We compare the result of the proposed method with that of the original Kohonen network. We further experiment the applicability and the performance of the method on dataset Iris. The result shows that the proposed method is able to produce satisfactory clustering results.