Neural networks have proved to be versatile and robust for particle separation in many experiments related to particle astrophysics. We apply these techniques to separate gamma rays from hadrons for the MAGIC Cerenkov Telescope. Two types of neural network architectures have been used for the classi cation task: one is the MultiLayer Perceptron (MLP) based on supervised learning, and the other is the Self-Organising Tree Algorithm (SOTA), which is based on unsupervised learning. We propose a new architecture by combining these two neural networks types to yield better and faster classi cation results for our classi cation problem.
@article{arxiv.astro-ph/0503539,
title = {Neural networks for gamma-hadron separation in MAGIC},
author = {P. Boinee and F. Barbarino and A. De Angelis and A. Saggion and M. Zacchello},
journal= {arXiv preprint arXiv:astro-ph/0503539},
year = {2015}
}
Comments
6 pages, 4 figures, to be published in the Proceedings of the 6th International Symposium ''Frontiers of Fundamental and Computational Physics'' (FFP6), Udine (Italy), Sep. 26-29, 2004