THE ASTROPHYSICAL JOURNAL, 446:300-317, 1995 June 10 NEURAL NETWORK CLASSIFICATION OF THE NEAR-INFRARED SPECTRA OF A-TYPE STARS WM. BRUCE WEAVER AND ANA V. TORRES-DODGEN Monterey Institute for Research in Astronomy (MIRA), 900 Major Sherman Lane, Monterey, CA 93940 ABSTRACT We present an atlas of near-infrared (NIR) spectra of A stars for luminosity classes Ia through V in the 15 A resolution system described by Torres-Dodgen and Weaver (1993, PASP, 105, 693) and demonstrate an accurate method to automatically classify A stars on this system. Using equivalent widths, artificial neural networks (ANNs) can classify these spectra to an accuracy of 0.4 types (subclasses) in temperature and 0.15 classes in luminosity. Using the spectrum, with no manual intervention except wavelength registration, ANNs can classify these spectra with an accuracy comparable to that of 2 A resolution MK classification: 0.5 types in temperature and 0.35 classes in luminosity. In addition, ANNs can concurrently determine reddening to an accuracy of 0.05 in E(B-V). We demonstrate that this NIR-ANN spectral classification system has the primary properties needed for automated classification surveys: it is based in the most efficient spectral region of modern silicon-based detectors, it requires low resolution (15 A) spectra to achieve sub-classification box accuracy, it can produce two dimensional classifications at least as accurate as those by expert human classifiers, it is relatively insensitive to interstellar reddening and can accurately determine the reddening, it can identify and classify composite spectra, it degrades slowly with decreasing signal-to-noise ratio, and it requires a minimum of human interaction at all stages of the process. Subject headings: atlases -- dust, extinction -- infrared: stars -- stars: fundamental parameters -- techniques: spectroscopic