AUTOMATED CLASSIFICATION OF STELLAR SPECTRA .1. INITIAL RESULTS WITH ARTIFICIAL NEURAL NETWORKS

We have initiated a project to classify stellar spectra automatically from high-dispersion objective prism plates. The automated technique p resented here is a simple back-propagation neural network, and is base d on the visual classification work of Houk. The plate material (Houk' s) is currently being digitized, and contains almost-equal-to 10(5) st ars down to V almost-equal-to 11 at almost-equal-to 2-angstrom resolut ion from almost-equal-to 3850 to 5150 angstrom. For this first paper i n the series we report on the results of 575 stars digitized from 6 pl ates. We find that even with the limited data set now in hand we can d etermine the temperature classification to better than 1.7 spectral su btypes from B3 to M4. Our current sample size provides insufficient tr aining set material to generate luminosity and metallicity classificat ions. Our eventual aims in this project are (1) to create a large and homogeneous digital stellar spectral library; (2) to create a well-und erstood and robust automatic classification algorithm which can determ ine temperatures, luminosities and metallicities for a wide variety of spectral types; (3) to use these data, supplemented by deeper plate m aterial, for the study of Galactic structure and chemical evolution; a nd (4) to find unusual or new classes of objects.