Classification and Ranking of Fermi LAT Gamma-Ray Sources from the 3FGL Catalog Using Machine Learning Techniques
P. M. Saz Parkinson et al 2016 ApJ 820 8
Machine learning techniques can classify Fermi/LAT sources as AGN or pulsars with >96% accuracy, and pulsars as young or millisecond with ~90% accuracy. This can be used to identify unassociated sources.