The self organizing map of neighbour stars and its kinematical interpretation

Abstract

The Self-Organizing Map (SOM) is a neural network algorithm that has the special property ofcreating spatially organized tepresetüatioes of various features of input signals. The resulting maps resemble realneural structures found in the cortices of developed animal brains.: Also, the SOM. has been successful in various pattern recognition tasks involving noisy signals, as for instance, speech recognition and for this reason we are studying its application to some astronomical problems. In this paper w~ present the 2-D mapping and subsequerít study of one local sample of 12000 stars using SOM. The available attributes are 14: 3-D position and velocitiesvphotometric indexes, spectral type and luminosity class. The possible location of halo, thick disk and thin disk stars is discussed. Their kinematical properties are also compared using the velocity distribution moments up to order four.