%0 Journal Article
%T Background rejection in NEXT using deep neural networks
%A NEXT Collaboration (Renner, J. et al
%A Benlloch-Rodriguez, J.
%A Botas, A.
%A Ferrario, P.
%A Gomez-Cadenas, J. J.
%A Alvarez, V.
%A Carcel, S.
%A Carrion, J. V.
%A Cervera-Villanueva, A.
%A Diaz, J.
%A Laing, A.
%A Liubarsky, I.
%A Lopez-March, N.
%A Lorca, D.
%A Martinez, A.
%A Monrabal, F.
%A Muñoz Vidal, J.
%A Nebot-Guinot, M.
%A Novella, P.
%A Palmeiro, B.
%A Querol, M.
%A Rodriguez, J.
%A Serra, L.
%A Simon, A.
%A Sorel, M.
%A Yahlali, N.
%J Journal of Instrumentation
%D 2017
%V 12
%I Iop Publishing Ltd
%@ 1748-0221
%G English
%F NEXTCollaborationRenner_etal2017
%O WOS:000395770200004
%O exported from refbase (https://references.ific.uv.es/refbase/show.php?record=2995), last updated on Mon, 15 Jun 2020 09:36:11 +0000
%X We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the use of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement.
%K Analysis and statistical methods
%K Pattern recognition
%K cluster finding
%K calibration and fitting methods
%K Double-beta decay detectors
%K Time projection chambers
%R 10.1088/1748-0221/12/01/T01004
%U http://arxiv.org/abs/1609.06202
%U https://doi.org/10.1088/1748-0221/12/01/T01004
%P T01004 - 21pp