AUTOMATED MORPHOLOGICAL CLASSIFICATION OF APM GALAXIES BY SUPERVISED ARTIFICIAL NEURAL NETWORKS

We train artificial neural networks to classify galaxies based solely on the morphology of the galaxy images as they appear on blue survey p lates. The images are reduced, and morphological features such as bulg e size and the number of arms are extracted, all in a fully automated manner. The galaxy sample was first classified by six independent expe rts. We use several definitions for the mean type of each galaxy, base d on those classifications. We then train and test the network on thes e features. We find that the rms error of the network classifications, as compared with the mean types of the expert classifications, is 1.8 Revised Hubble types. This is comparable to the overall rms dispersio n between the experts. This result is robust and almost completely ind ependent of the network architecture used.