Probing Neural Networks for the Gamma/Hadron Separation of the Cherenkov Telescope Array
arXiv:1907.02428 · doi:10.1088/1742-6596/1525/1/012084
Abstract
We compared convolutional neural networks to the classical boosted decision trees for the separation of atmospheric particle showers generated by gamma rays from the particle-induced background. We conduct the comparison of the two techniques applied to simulated observation data from the Cherenkov Telescope Array. We then looked at the Receiver Operating Characteristics (ROC) curves produced by the two approaches and discuss the similarities and differences between both. We found that neural networks overperformed classical techniques under specific conditions.
arXiv comment6 pages, submitted on May 06 2019 to PoS as proceedings of ACAT2019
References in corpus (8)
- The Pierre Auger Cosmic Ray Observatory
- Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
- A high performance likelihood reconstruction of gamma-rays for Imaging Atmospheric Cherenkov Telescopes
- Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
- Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
- Deep Convolutional Neural Networks as strong gravitational lens detectors
- A Deep Learning-based Reconstruction of Cosmic Ray-induced Air Showers
- PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light