Playing tag with ANN: boosted top identification with pattern recognition

  • Leandro G. Almeida
  • Mihailo Backović
  • Mathieu Cliche
  • Seung J. Lee
  • Maxim PerelsteinEmail author
Open Access
Regular Article - Theoretical Physics


Many searches for physics beyond the Standard Model at the Large Hadron Collider (LHC) rely on top tagging algorithms, which discriminate between boosted hadronic top quarks and the much more common jets initiated by light quarks and gluons. We note that the hadronic calorimeter (HCAL) effectively takes a “digital image” of each jet, with pixel intensities given by energy deposits in individual HCAL cells. Viewed in this way, top tagging becomes a canonical pattern recognition problem. With this motivation, we present a novel top tagging algorithm based on an Artificial Neural Network (ANN), one of the most popular approaches to pattern recognition. The ANN is trained on a large sample of boosted tops and light quark/gluon jets, and is then applied to independent test samples. The ANN tagger demonstrated excellent performance in a Monte Carlo study: for example, for jets with p T in the 1100-1200 GeV range, 60% top-tag efficiency can be achieved with a 4% mis-tag rate. We discuss the physical features of the jets identified by the ANN tagger as the most important for classification, as well as correlations between the ANN tagger and some of the familiar top-tagging observables and algorithms.




Open Access

This article is distributed under the terms of the Creative Commons Attribution License (CC-BY 4.0), which permits any use, distribution and reproduction in any medium, provided the original author(s) and source are credited.


  1. [1]
    G. Perez, Top quark theory and the new physics searches frontier, Phys. Scripta T158 (2013) 014008 [INSPIRE].ADSCrossRefGoogle Scholar
  2. [2]
    K. Agashe, A. Belyaev, T. Krupovnickas, G. Perez and J. Virzi, LHC Signals from Warped Extra Dimensions, Phys. Rev. D 77 (2008) 015003 [hep-ph/0612015] [INSPIRE].ADSGoogle Scholar
  3. [3]
    B. Lillie, L. Randall and L.-T. Wang, The Bulk RS KK-gluon at the LHC, JHEP 09 (2007) 074 [hep-ph/0701166] [INSPIRE].ADSCrossRefGoogle Scholar
  4. [4]
    M. Perelstein and A. Spray, Four boosted tops from a Regge gluon, JHEP 09 (2011) 008 [arXiv:1106.2171] [INSPIRE].ADSCrossRefzbMATHGoogle Scholar
  5. [5]
    T. Plehn, M. Spannowsky, M. Takeuchi and D. Zerwas, Stop Reconstruction with Tagged Tops, JHEP 10 (2010) 078 [arXiv:1006.2833] [INSPIRE].ADSCrossRefGoogle Scholar
  6. [6]
    J. Berger, M. Perelstein, M. Saelim and A. Spray, Boosted Tops from Gluino Decays, arXiv:1111.6594 [INSPIRE].
  7. [7]
    A. Azatov, M. Salvarezza, M. Son and M. Spannowsky, Boosting Top Partner Searches in Composite Higgs Models, Phys. Rev. D 89 (2014) 075001 [arXiv:1308.6601] [INSPIRE].ADSGoogle Scholar
  8. [8]
    T. Flacke, J.H. Kim, S.J. Lee and S.H. Lim, Constraints on composite quark partners from Higgs searches, JHEP 05 (2014) 123 [arXiv:1312.5316] [INSPIRE].ADSCrossRefGoogle Scholar
  9. [9]
    M. Backović, G. Perez, T. Flacke and S.J. Lee, LHC Top Partner Searches Beyond the 2 TeV Mass Region, arXiv:1409.0409 [INSPIRE].
  10. [10]
    M. Backović, T. Flacke, J.H. Kim and S.J. Lee, Boosted Event Topologies from TeV Scale Light Quark Composite Partners, JHEP 04 (2015) 082 [arXiv:1410.8131] [INSPIRE].ADSCrossRefGoogle Scholar
  11. [11]
    B. Gripaios, T. Müller, M.A. Parker and D. Sutherland, Search Strategies for Top Partners in Composite Higgs models, JHEP 08 (2014) 171 [arXiv:1406.5957] [INSPIRE].ADSCrossRefGoogle Scholar
  12. [12]
    J. Reuter and M. Tonini, Top Partner Discovery in the TtZ channel at the LHC, JHEP 01 (2015) 088 [arXiv:1409.6962] [INSPIRE].ADSCrossRefGoogle Scholar
  13. [13]
    T. Plehn and M. Spannowsky, Top Tagging, J. Phys. G 39 (2012) 083001 [arXiv:1112.4441] [INSPIRE].ADSCrossRefGoogle Scholar
  14. [14]
    A. Altheimer et al., Jet Substructure at the Tevatron and LHC: New results, new tools, new benchmarks, J. Phys. G 39 (2012) 063001 [arXiv:1201.0008] [INSPIRE].ADSCrossRefGoogle Scholar
  15. [15]
    M. Jankowiak and A.J. Larkoski, Jet Substructure Without Trees, JHEP 06 (2011) 057 [arXiv:1104.1646] [INSPIRE].ADSCrossRefGoogle Scholar
  16. [16]
    J.D. Bjorken and S.J. Brodsky, Statistical Model for electron-Positron Annihilation Into Hadrons, Phys. Rev. D 1 (1970) 1416 [INSPIRE].ADSGoogle Scholar
  17. [17]
    J. Thaler and L.-T. Wang, Strategies to Identify Boosted Tops, JHEP 07 (2008) 092 [arXiv:0806.0023] [INSPIRE].ADSCrossRefGoogle Scholar
  18. [18]
    L.G. Almeida, S.J. Lee, G. Perez, G.F. Sterman, I. Sung and J. Virzi, Substructure of high-pT Jets at the LHC, Phys. Rev. D 79 (2009) 074017 [arXiv:0807.0234] [INSPIRE].ADSGoogle Scholar
  19. [19]
    J.M. Butterworth, A.R. Davison, M. Rubin and G.P. Salam, Jet substructure as a new Higgs search channel at the LHC, Phys. Rev. Lett. 100 (2008) 242001 [arXiv:0802.2470] [INSPIRE].ADSCrossRefGoogle Scholar
  20. [20]
    D. Krohn, J. Thaler and L.-T. Wang, Jet Trimming, JHEP 02 (2010) 084 [arXiv:0912.1342] [INSPIRE].ADSCrossRefGoogle Scholar
  21. [21]
    S.D. Ellis, C.K. Vermilion and J.R. Walsh, Recombination Algorithms and Jet Substructure: Pruning as a Tool for Heavy Particle Searches, Phys. Rev. D 81 (2010) 094023 [arXiv:0912.0033] [INSPIRE].ADSGoogle Scholar
  22. [22]
    T. Plehn, G.P. Salam and M. Spannowsky, Fat Jets for a Light Higgs, Phys. Rev. Lett. 104 (2010) 111801 [arXiv:0910.5472] [INSPIRE].ADSCrossRefGoogle Scholar
  23. [23]
    D.E. Kaplan, K. Rehermann, M.D. Schwartz and B. Tweedie, Top Tagging: A Method for Identifying Boosted Hadronically Decaying Top Quarks, Phys. Rev. Lett. 101 (2008) 142001 [arXiv:0806.0848] [INSPIRE].ADSCrossRefGoogle Scholar
  24. [24]
    J. Thaler and K. Van Tilburg, Identifying Boosted Objects with N-subjettiness, JHEP 03 (2011) 015 [arXiv:1011.2268] [INSPIRE].ADSCrossRefGoogle Scholar
  25. [25]
    J. Thaler and K. Van Tilburg, Maximizing Boosted Top Identification by Minimizing N-subjettiness, JHEP 02 (2012) 093 [arXiv:1108.2701] [INSPIRE].ADSCrossRefGoogle Scholar
  26. [26]
    L.G. Almeida, O. Erdogan, J. Juknevich, S.J. Lee, G. Perez and G. Sterman, Three-particle templates for a boosted Higgs boson, Phys. Rev. D 85 (2012) 114046 [arXiv:1112.1957] [INSPIRE].ADSGoogle Scholar
  27. [27]
    L.G. Almeida, S.J. Lee, G. Perez, G. Sterman and I. Sung, Template Overlap Method for Massive Jets, Phys. Rev. D 82 (2010) 054034 [arXiv:1006.2035] [INSPIRE].ADSGoogle Scholar
  28. [28]
    M. Backovic, J. Juknevich and G. Perez, Boosting the Standard Model Higgs Signal with the Template Overlap Method, JHEP 07 (2013) 114 [arXiv:1212.2977] [INSPIRE].ADSCrossRefGoogle Scholar
  29. [29]
    M. Backovic, O. Gabizon, J. Juknevich, G. Perez and Y. Soreq, Measuring boosted tops in semi-leptonic \( t\overline{t} \) events for the standard model and beyond, JHEP 04 (2014) 176 [arXiv:1311.2962] [INSPIRE].ADSCrossRefGoogle Scholar
  30. [30]
    D0 collaboration, V.M. Abazov et al., A precision measurement of the mass of the top quark, Nature 429 (2004) 638 [hep-ex/0406031] [INSPIRE].
  31. [31]
    P. Artoisenet, V. Lemaitre, F. Maltoni and O. Mattelaer, Automation of the matrix element reweighting method, JHEP 12 (2010) 068 [arXiv:1007.3300] [INSPIRE].ADSCrossRefzbMATHGoogle Scholar
  32. [32]
    D.E. Soper and M. Spannowsky, Finding physics signals with shower deconstruction, Phys. Rev. D 84 (2011) 074002 [arXiv:1102.3480] [INSPIRE].ADSGoogle Scholar
  33. [33]
    D.E. Soper and M. Spannowsky, Finding top quarks with shower deconstruction, Phys. Rev. D 87 (2013) 054012 [arXiv:1211.3140] [INSPIRE].ADSGoogle Scholar
  34. [34]
    A.J. Larkoski, S. Marzani, G. Soyez and J. Thaler, Soft Drop, JHEP 05 (2014) 146 [arXiv:1402.2657] [INSPIRE].ADSCrossRefGoogle Scholar
  35. [35]
    ATLAS collaboration, A search for \( t\overline{t} \) resonances in lepton+jets events with highly boosted top quarks collected in pp collisions at \( \sqrt{s}=7 \) TeV with the ATLAS detector, JHEP 09 (2012) 041 [arXiv:1207.2409] [INSPIRE].
  36. [36]
    ATLAS collaboration, Search for resonances decaying into top-quark pairs using fully hadronic decays in pp collisions with ATLAS at \( \sqrt{s}=7 \) TeV, JHEP 01 (2013) 116 [arXiv:1211.2202] [INSPIRE].
  37. [37]
    CMS collaboration, A Cambridge-Aachen (C-A) based Jet Algorithm for boosted top-jet tagging, CMS-PAS-JME-09-001 (2009).
  38. [38]
    CMS collaboration, Jet Substructure Algorithms, CMS-PAS-JME-10-013 (2011).
  39. [39]
    J. Cogan, M. Kagan, E. Strauss and A. Schwarztman, Jet-Images: Computer Vision Inspired Techniques for Jet Tagging, JHEP 02 (2015) 118 [arXiv:1407.5675] [INSPIRE].ADSCrossRefGoogle Scholar
  40. [40]
    I.M. Dremin, G.K. Eyyubova, V.L. Korotkikh and L.I. Sarycheva, Two-dimensional discrete wavelet analysis of multiparticle event topology in heavy ion collisions, Indian J. Phys. 85 (2011) 39 [arXiv:0711.1657] [INSPIRE].ADSCrossRefGoogle Scholar
  41. [41]
    I. Volobouev, FFTJet: A Package for Multiresolution Particle Jet Reconstruction in the Fourier Domain, arXiv:0907.0270 [INSPIRE].
  42. [42]
    V. Rentala, W. Shepherd and T.M.P. Tait, Tagging Boosted Ws with Wavelets, JHEP 08 (2014) 042 [arXiv:1404.1929] [INSPIRE].ADSCrossRefGoogle Scholar
  43. [43]
    J.W. Monk, Wavelet Analysis: Event De-noising, Shower Evolution and Jet Substructure Without Jets, arXiv:1405.5008 [INSPIRE].
  44. [44]
    F. Maltoni and T. Stelzer, MadEvent: Automatic event generation with MadGraph, JHEP 02 (2003) 027 [hep-ph/0208156] [INSPIRE].ADSCrossRefGoogle Scholar
  45. [45]
    T. Sjöstrand, S. Mrenna and P.Z. Skands, PYTHIA 6.4 Physics and Manual, JHEP 05 (2006) 026 [hep-ph/0603175] [INSPIRE].ADSCrossRefzbMATHGoogle Scholar
  46. [46]
    T. Sjöstrand, S. Mrenna and P.Z. Skands, A Brief Introduction to PYTHIA 8.1, Comput. Phys. Commun. 178 (2008) 852 [arXiv:0710.3820] [INSPIRE].ADSCrossRefzbMATHGoogle Scholar
  47. [47]
    M. Cacciari, G.P. Salam and G. Soyez, FastJet User Manual, Eur. Phys. J. C 72 (2012) 1896 [arXiv:1111.6097] [INSPIRE].ADSCrossRefGoogle Scholar
  48. [48]
    M. Cacciari, G.P. Salam and G. Soyez, The anti-kt jet clustering algorithm, JHEP 04 (2008) 063 [arXiv:0802.1189] [INSPIRE].ADSCrossRefzbMATHGoogle Scholar
  49. [49]
    C.M. Bishop, Neural Networks for Pattern Recognition, fist edition, Oxford University Press, Oxford U.K. (1996).Google Scholar
  50. [50]
    P. Werbos, Beyond regression: new tools for prediction and analysis in the behavioral sciences, Ph.D. Thesis, Harvard University, U.S.A. (1975).Google Scholar
  51. [51]
    S. Marsland, Machine Learning: An Algorithmic Perspective, first edition, Chapman & Hall/CRC, (2009).Google Scholar
  52. [52]
    Y. Freund and R.E. Schapire, A short introduction to boosting, in In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, Morgan Kaufmann, (1999), pp. 1401-1406.Google Scholar
  53. [53]
    A.J. Larkoski and J. Thaler, Unsafe but Calculable: Ratios of Angularities in Perturbative QCD, JHEP 09 (2013) 137 [arXiv:1307.1699] [INSPIRE].ADSCrossRefGoogle Scholar
  54. [54]
    A. Hook, E. Izaguirre, M. Lisanti and J.G. Wacker, High Multiplicity Searches at the LHC Using Jet Masses, Phys. Rev. D 85 (2012) 055029 [arXiv:1202.0558] [INSPIRE].ADSGoogle Scholar
  55. [55]
    T. Cohen, E. Izaguirre, M. Lisanti and H.K. Lou, Jet Substructure by Accident, JHEP 03 (2013) 161 [arXiv:1212.1456] [INSPIRE].ADSCrossRefGoogle Scholar
  56. [56]
    M. Backović and J. Juknevich, TemplateTagger v1.0.0: A Template Matching Tool for Jet Substructure, Comput. Phys. Commun. 185 (2014) 1322 [arXiv:1212.2978] [INSPIRE].ADSCrossRefGoogle Scholar
  57. [57]
    ATLAS collaboration, Search for \( t\overline{t} \) resonances in the lepton plus jets final state with ATLAS using 4.7 fb−1 of pp collisions at \( \sqrt{s}=7 \) TeV, Phys. Rev. D 88 (2013) 012004 [arXiv:1305.2756] [INSPIRE].

Copyright information

© The Author(s) 2015

Authors and Affiliations

  • Leandro G. Almeida
    • 1
  • Mihailo Backović
    • 2
  • Mathieu Cliche
    • 3
  • Seung J. Lee
    • 4
    • 5
  • Maxim Perelstein
    • 3
    Email author
  1. 1.Institut de Biologie de l’ École Normale Supérieure (IBENS), Inserm 1024- CNRS 8197ParisFrance
  2. 2.Center for CosmologyParticle Physics and Phenomenology - CP3, Universite Catholique de LouvainLouvain-la-neuveBelgium
  3. 3.Laboratory for Elementary Particle PhysicsCornell UniversityIthacaUnited States
  4. 4.Department of PhysicsKorea Advanced Institute of Science and TechnologyDaejeonSouth Korea
  5. 5.School of PhysicsKorea Institute for Advanced StudySeoulSouth Korea

Personalised recommendations