The automated classification of astronomical light curves using Kohonen self-organizing maps

We apply the technique of self-organizing maps to the automated classification of singly periodic astronomical light curves. We find that our maps readily distinguish between light curve types in both synthetic and real data sets, and that the resulting maps do not depend sensitively on the chosen learning parameters. Automated data analysis techniques are likely to be become increasingly important as the size of astronomical data sets continues to increase, particularly with the advent of ultra-wide-field survey telescopes such as WASP, RAPTOR and ASAS.