A self-organizing neural network model for the simultaneous development of topographic receptive elds and lateral interactions in cortical maps is presented. Both aaerent and lateral connections adapt by the same Hebbian mechanism in a purely local and unsupervised learning process. AAerent input weights of each neuron self-organize into hill-shaped prooles, receptive elds organize topographica...

This article is an extended version of a paper presented in the WSOM’2012 conference [1]. We display a combination of factorial projections, SOM algorithm and graph techniques applied to a text mining problem. The corpus contains 8 medieval manuscripts which were used to teach arithmetic techniques to merchants. Among the techniques for Data Analysis, those used for Lexicometry (such as Factori...

In this article, the use of the self-organizing map (SOM) is approached on the basis of current theories of learning. Possibilities of computer and networked platforms that aim at helping human learning are also inspected. It is shown how the SOM can be considered a model of constructive learning. The area of constructive learning is outlined and two cases of using the self-organizing map in co...