%0 Journal Article %T Performance of top-quark and W-boson tagging with ATLAS in Run 2 of the LHC %A ATLAS Collaboration (Aaboud, M. et al %A Alvarez Piqueras, D. %A Aparisi Pozo, J. A. %A Bailey, A. J. %A Barranco Navarro, L. %A Cabrera Urban, S. %A Castillo, F. L. %A Castillo Gimenez, V. %A Cerda Alberich, L. %A Costa, M. J. %A Escobar, C. %A Estrada Pastor, O. %A Ferrer, A. %A Fiorini, L. %A Fullana Torregrosa, E. %A Fuster, J. %A Garcia, C. %A Garcia Navarro, J. E. %A Gonzalez de la Hoz, S. %A Gonzalvo Rodriguez, G. R. %A Higon-Rodriguez, E. %A Jimenez Pena, J. %A Lacasta, C. %A Lozano Bahilo, J. J. %A Madaffari, D. %A Mamuzic, J. %A Marti-Garcia, S. %A Melini, D. %A MiƱano, M. %A Mitsou, V. A. %A Rodriguez Bosca, S. %A Rodriguez Rodriguez, D. %A Ruiz-Martinez, A. %A Salt, J. %A Santra, A. %A Soldevila, U. %A Sanchez, J. %A Valero, A. %A Valls Ferrer, J. A. %A Vos, M. %J European Physical Journal C %D 2019 %V 79 %N 5 %I Springer %@ 1434-6044 %G English %F ATLASCollaborationAaboud_etal2019 %O WOS:000466407600007 %O exported from refbase (https://references.ific.uv.es/refbase/show.php?record=4073), last updated on Wed, 17 Jul 2019 10:01:50 +0000 %X The performance of identification algorithms (taggers) for hadronically decaying top quarks and W bosons in pp collisions at = 13TeV recorded by the ATLAS experiment at the Large Hadron Collider is presented. A set of techniques based on jet shape observables are studied to determine a set of optimal cut-based taggers for use in physics analyses. The studies are extended to assess the utility of combinations of substructure observables as a multivariate tagger using boosted decision trees or deep neural networks in comparison with taggers based on two-variable combinations. In addition, for highly boosted top-quark tagging, a deep neural network based on jet constituent inputs as well as a re-optimisation of the shower deconstruction technique is presented. The performance of these taggers is studied in data collected during 2015 and 2016 corresponding to 36.1fb-1 for the tt and +jet and 36.7-1 for the dijet event topologies. %R 10.1140/epjc/s10052-019-6847-8 %U https://arxiv.org/abs/1808.07858 %U https://doi.org/10.1140/epjc/s10052-019-6847-8 %P 375-54pp