Local competitive signals for an unsupervised competitive neural network

Unsupervised Competitive Neural Networks (UCN) have been recognized as a powerful tool for pattern analysis, feature extraction and clustering analysis. Nevertheless, the inhibitory interactions among the units of the network, required by the winner-take-all paradigm, constitute a crucial step for the implementation of competitive networks in analog VLSI. The aim of this paper is to present an unsupervised competitive neural network characterized by local inhibitory interactions among its cells. The kernel of this network is a neural unit based on a modified competitive learning law in which the threshold changes in the learning stage. It is shown that the proposed neuron unit is able, during the learning stage, to perform an automatic selection of patterns that belong to a cluster, moving towards its centroid. The properties of this network, related to the robustness of the final results and to the choice of the number of the elements, are examined in a set of numerical simulations adopting a data set composed of Gaussian mixtures and uniform noise