Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment

A b-jet identification algorithm is constructed with a Recurrent Neural Network (RNN) at the ATLAS experiment at the CERN Large Hadron Collider. The RNN based b-tagging algorithm processes charged particle tracks associated to jets without reliance on secondary vertex finding, and can augment secondary-vertex based taggers. In contrast to traditional impact-parameter-based b-tagging algorithms which assume that tracks associated to jets are independent from each other, the RNN based b-tagging algorithm can exploit the spatial and kinematic correlations between tracks which are initiated from the same b-hadron. This new approach also accommodates an extended set of input variables. This note presents the expected performance of the RNN based b-tagging algorithm in simulated tt̄ events created in proton–proton collisions at √ s = 13 TeV. © 2017 CERN for the benefit of the ATLAS Collaboration. Reproduction of this article or parts of it is allowed as specified in the CC-BY-3.0 license.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[3]  J. Huston,et al.  New generation of parton distributions with uncertainties from global QCD analysis , 2002, hep-ph/0201195.

[4]  Sepp Hochreiter,et al.  Untersuchungen zu dynamischen neuronalen Netzen , 1991 .

[5]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[6]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[7]  T. Koi,et al.  Reconstruction of hadronic decay products of tau leptons with the ATLAS experiment , 2015, The European Physical Journal. C, Particles and Fields.

[8]  D. Lange,et al.  The EvtGen particle decay simulation package , 2001 .

[9]  Peter Skands,et al.  A brief introduction to PYTHIA 8.1 , 2007, Comput. Phys. Commun..

[10]  J. Huston,et al.  New parton distributions for collider physics , 2010, 1007.2241.

[11]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[12]  J. T. Childers,et al.  The ATLAS Simulation Infrastructure , 2010, 1005.4568.

[13]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[14]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[15]  J. T. Childers,et al.  Identification and energy calibration of hadronically decaying tau leptons with the ATLAS experiment in pp collisions at \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \ , 2014, The European Physical Journal. C, Particles and Fields.

[16]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[17]  A. Goshaw.  The ATLAS Experiment at the CERN Large Hadron Collider , 2008 .

[18]  Aniello De Santo,et al.  Performance of $b$-Jet Identification in the ATLAS Experiment , 2016 .

[19]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[20]  P. Skands.  Tuning Monte Carlo Generators: The Perugia Tunes , 2010, 1005.3457.

[21]  A. Dell'Acqua,et al.  Geant4 - A simulation toolkit , 2003 .

[22]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[24]  P. Nason.  A new method for combining NLO QCD with shower Monte Carlo algorithms , 2004, hep-ph/0409146.

[25]  Y. Coadou,et al.  Optimisation of the ATLAS $b$-tagging performance for the 2016 LHC Run , 2016 .

[26]  M. Cacciari,et al.  A pr 2 00 8 The anti-k t jet clustering algorithm , 2008 .