\begin{thebibliography}{10} \bibitem{akrawy1989measurement} MZ~Akrawy, G~Alexander, J~Allison, PP~Allport, KJ~Anderson, JC~Armitage, GTJ Arnison, P~Ashton, G~Azuelos, JTM Baines, et~al. \newblock Measurement of the z0 mass and width with the opal detector at lep. \newblock {\em Physics Letters B}, 231(4):530--538, 1989. \bibitem{thomson2013modern} Mark Thomson. \newblock {\em Modern particle physics}. \newblock Cambridge University Press, 2013. \bibitem{abe2008precision} S~Abe, T~Ebihara, S~Enomoto, K~Furuno, Y~Gando, K~Ichimura, H~Ikeda, K~Inoue, Y~Kibe, Y~Kishimoto, et~al. \newblock Precision measurement of neutrino oscillation parameters with kamland. \newblock {\em Physical Review Letters}, 100(22):221803, 2008. \bibitem{adamson2011measurement} P~Adamson, C~Andreopoulos, R~Armstrong, DJ~Auty, DS~Ayres, C~Backhouse, G~Barr, M~Bishai, A~Blake, GJ~Bock, et~al. \newblock Measurement of the neutrino mass splitting and flavor mixing by minos. \newblock {\em Physical Review Letters}, 106(18):181801, 2011. \bibitem{blondel2013research} A~Blondel, A~Bravar, M~Pohl, S~Bachmann, N~Berger, M~Kiehn, A~Sch{\"o}ning, D~Wiedner, B~Windelband, P~Eckert, et~al. \newblock Research proposal for an experiment to search for the decay $\mu \rightarrow eee$. \newblock {\em arXiv preprint arXiv:1301.6113}, 2013. \bibitem{augustin2017mupix} Heiko Augustin, Niklaus Berger, Sebastian Dittmeier, Carsten Grzesik, Jan Hammerich, Qinhua Huang, Lennart Huth, Moritz Kiehn, Alexandr Kozlinskiy, Frank~Meier Aeschbacher, et~al. \newblock The mupix system-on-chip for the mu3e experiment. \newblock {\em Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment}, 845:194--198, 2017. \bibitem{philipp2015hv} Jonathan Philipp, Lennart Huth, Heiko Augustin, Raphael Philipp, Dirk Wiedner, Niklaus Berger, Mu3e Collaboration, et~al. \newblock Das hv-maps basierte mupix teleskop. \newblock Technical report, Detector RD at DESY Test beam, 2015. \bibitem{augustin2015mupix} Heiko Augustin, N~Berger, S~Bravar, Simon Corrodi, A~Damyanova, F~F{\"o}rster, R~Gredig, A~Herkert, Q~Huang, L~Huth, et~al. \newblock The mupix high voltage monolithic active pixel sensor for the mu3e experiment. \newblock {\em Journal of Instrumentation}, 10(03):C03044, 2015. \bibitem{connor1994recurrent} Jerome~T Connor, R~Douglas Martin, and Les~E Atlas. \newblock Recurrent neural networks and robust time series prediction. \newblock {\em IEEE transactions on neural networks}, 5(2):240--254, 1994. \bibitem{grossberg2013recurrent} Stephen Grossberg. \newblock Recurrent neural networks. \newblock {\em Scholarpedia}, 8(2):1888, 2013. \bibitem{ML:XGBoost} Tianqi Chen and Carlos Guestrin. \newblock Xgboost: {A} scalable tree boosting system. \newblock {\em CoRR}, abs/1603.02754, 2016. \bibitem{chollet2015keras} Fran{\c{c}}ois Chollet et~al. \newblock Keras: Deep learning library for theano and tensorflow. \newblock {\em URL: https://keras. io/k}, 7(8), 2015. \bibitem{abadi2016tensorflow} Mart{\'\i}n Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et~al. \newblock Tensorflow: a system for large-scale machine learning. \newblock In {\em OSDI}, volume~16, pages 265--283, 2016. \bibitem{klambauer2017self} G{\"u}nter Klambauer, Thomas Unterthiner, Andreas Mayr, and Sepp Hochreiter. \newblock Self-normalizing neural networks. \newblock In {\em Advances in Neural Information Processing Systems}, pages 971--980, 2017. \bibitem{chilimbi2014project} Trishul~M Chilimbi, Yutaka Suzue, Johnson Apacible, and Karthik Kalyanaraman. \newblock Project adam: Building an efficient and scalable deep learning training system. \newblock In {\em OSDI}, volume~14, pages 571--582, 2014. \bibitem{ioffe2015batch} Sergey Ioffe and Christian Szegedy. \newblock Batch normalization: Accelerating deep network training by reducing internal covariate shift. \newblock {\em arXiv preprint arXiv:1502.03167}, 2015. \bibitem{cooijmans2016recurrent} Tim Cooijmans, Nicolas Ballas, C{\'e}sar Laurent, {\c{C}}a{\u{g}}lar G{\"u}l{\c{c}}ehre, and Aaron Courville. \newblock Recurrent batch normalization. \newblock {\em arXiv preprint arXiv:1603.09025}, 2016. \bibitem{schuster1997bidirectional} Mike Schuster and Kuldip~K Paliwal. \newblock Bidirectional recurrent neural networks. \newblock {\em IEEE Transactions on Signal Processing}, 45(11):2673--2681, 1997. \bibitem{gers1999learning} Felix~A Gers, J{\"u}rgen Schmidhuber, and Fred Cummins. \newblock Learning to forget: Continual prediction with lstm. \newblock 1999. \bibitem{chung2014empirical} Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. \newblock Empirical evaluation of gated recurrent neural networks on sequence modeling. \newblock {\em arXiv preprint arXiv:1412.3555}, 2014. \bibitem{agostinelli2003s} S~Agostinelli. \newblock S. agostinelli et al.(geant4 collaboration), nucl. instrum. methods phys. res., sect. a 506, 250 (2003). \newblock {\em Nucl. Instrum. Methods Phys. Res., Sect. A}, 506:250, 2003. \bibitem{pedregosa2011scikit} Fabian Pedregosa, Ga{\"e}l Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et~al. \newblock Scikit-learn: Machine learning in python. \newblock {\em Journal of machine learning research}, 12(Oct):2825--2830, 2011. \bibitem{ML:ROC_AUC:Bradley:1997:UAU:1746432.1746434} Andrew~P. Bradley. \newblock The use of the area under the roc curve in the evaluation of machine learning algorithms. \newblock {\em Pattern Recogn.}, 30(7):1145--1159, July 1997. \bibitem{gent1992special} CR~Gent and CP~Sheppard. \newblock Special feature. predicting time series by a fully connected neural network trained by back propagation. \newblock {\em Computing \& Control Engineering Journal}, 3(3):109--112, 1992. \bibitem{graves2013speech} Alex Graves, Abdel-rahman Mohamed, and Geoffrey Hinton. \newblock Speech recognition with deep recurrent neural networks. \newblock In {\em Acoustics, speech and signal processing (icassp), 2013 ieee international conference on}, pages 6645--6649. IEEE, 2013. \end{thebibliography}