Аннотация:In this work, the ability of rare VHE gamma ray selection with neural network methods isinvestigated in the case when cosmic radiation flux strongly prevails (ratio up to 104 over the gammaradiation flux from a point source). This ratio is valid for the Crab Nebula in the TeV energy range,since the Crab is a well-studied source for calibration and test of various methods and installations ingamma astronomy. The part of TAIGA experiment which includes three Imaging Atmospheric CherenkovTelescopes observes this gamma-source too. Cherenkov telescopes obtain images of Extensive AirShowers. Hillas parameters can be used to analyse images in standard processing method, or images canbe processed with convolutional neural networks. In this work we would like to describe the main steps andresults obtained in the gamma/hadron separation task from the Crab Nebula with neural network methods.The results obtained are compared with standard processing method applied in the TAIGA collaborationand using Hillas parameter cuts. It is demonstrated that a signal was received at the level of higher than5.5σ in 21 h of Crab Nebula observations after processing the experimental data with the neural network method.Keywords: gamma astronomy, IACT, image recognition, convolutional neural networks, Crab Nebula
