Clustering is a branch of multivariate analysis that is used to create groups of data. Most of the existing clustering techniques require defining additional information, including the actual number of clusters, before they can be carried out. This article presents a novel neural network that is capable of creating groups by using a combination of hierarchical clustering and self-organizing maps, without requiring the number of existing clusters to be specified beforehand. The self-organized cluster automatic detection neural network is described in detail, focusing on the density, the average distance, the division algorithm, the update algorithm and the training phase. Three case studies have been carried out in this research in order to evaluate the performance of the neural network, and the results obtained are presented within this article.