Artificial Neural Networks as a Tool for Galaxy Classification

Abstract

We describe an Artificial Neural Network (ANN) approach to classification of galaxy images and spectra. ANNs can replicate the classification of galaxy images by a human expert to the same degree of agreement as that between two human experts, to within 2 T-type units. Similar methods are applied to classification of galaxy spectra. In particular, Principal Component Analysis of galaxy spectra can be used to compress the data, to suppress noise and to provide input to the ANNs. These and other classification methods will soon be applied to the Anglo-Australian 2-degree-Field (2dF) redshift survey of 250,000 galaxies.