2005BaltA..14..351C

The application of supervised artificial neural networks (ANNs) for quasar selection is investigated, using the list of candidates and their classification from White et al. (2000). The adopted architectures are 7:1 and 7:2:1, both with seven input parameters (optical and radio data from APM POSS-I (E and O plates) and VLA/FIRST) and a single output interpreted as a quasar probability. Both models were trained on samples of ∼800 sources and yielded similar performance on independent test samples, with reliability as large as 90 to 80% for completeness from 70 to 90%. For comparison, the quasar fraction in the original list of candidates was 56%. The accuracy found with ANNs is similar to that obtained by White et al. using decision trees and training samples of similar size. Predictions of the probabilities for the 98 candidates without spectroscopic classification in White et al. are presented, showing a good agreement between the two ANN models and with the values obtained by White et al. This work presents the first analysis of the performance of ANNs for quasar selection, showing that ANNs provide a promising technique to single out specific object types in astronomical databases.