Classification of the hadronic decays of the Z0 into b and c quark pairs using a neural network

Abreu, P.; Adam, W.; Adye, T.; Agasi, E.; Alekseev, G. D.; Algeri, A.; Allen, P.; Almehed, S.; Alvsvaag, S. J.; Amaldi, U.; Anassontzis, E.; Andreazza, A.; Antilogus, P.; Apel, W. D.; Apsimon, R.; Åsman, B.; Augustin, J.-E.; Augustinus, A.; Baillon, P.; Bambade, P.; Barão, F.; Barate, R.; Barbiellini, G.; Bardin, D. Y.; Barker, G. J.; Baroncelli, A.; Bärring, O.; Barrio, J. A.; Bartl, W.; Bates, M. J.; Battaglia, M.; Baubillier, M.; Becks, K. H.; Beeston, C.; Begalli, M.; Beillière, P.; Belokopytov, Yu.; Beltran, P.; Benedic, D.; Benvenuti, A. C.; Berggren, M.; Bertrand, Daniel; Bianchi, F.; Bilenkii, M.S.; Billoir, P.; Bjarne, J.; Blöch, D.; Blyth, S.; Bocci, V.; Bogolubov, P. N.; Bolognese, T.; Bonesini, M.; Bonivento, W.; Booth, P.S.L.; Borgeaud, P.; Borisov, G.; Borner, H.; Bosio, C.; Boštjančič, B.; Bosworth, S.; Botner, O.; Bouquet, B.; Bourdarios, C.; Bowcock, T. J. V.; Bozzo, M.; Braibant, S.; Branchini, P.; Brand, K. D.; Brenner, R.; Briand, H.; Bricman, C.; Brown, R.C.A.; Brümmer, N.; Brunet, J. M.; Bugge, L.; Buran, T.; Burmeister, H.; Buytaert, J.; Caccia, M.; Calvi, M.; Rozas, Aurelio Juste; Camporesi, T.; Canale, V.; Cao, F.; Carena, F.; Carroll, L.; Caso, C.; Gimenez, M. V. Castillo; Cattai, A.; Cavallo, F. R.; Cerrito, L.; Chabaud, V.; Chan, A.; Charpentier, Ph.; Chaussard, L.; Chauveau, J.; Checchia, P.; Chelkov, G. A.; Chevalier, L.; Chliapnikov, P.; Chorowicz, V.; Chrin, J.; Ciuchini, M.; Clara, M.P.; Collins, P.; Contreras, J. L.; Contri, R.; Cortina, E.; Cosme, G.; Cosmo, G.; Couchot, F.; Crawley, H. B.; Crennell, D.; Crosetti, G.; Crozon, M.; Cuevas, J.; Czellár, S.; Dahl‐Jensen, E.; Dalmagne, B.; Dam, M.; Damgaard, G.; Darbo, G.; Daubie, E.; Daum, A.; Dauncey, P. D.; Davenport, M.; David, P.; Silva, W. da; Defoix, C.; Delikaris, D.; Delorme, Stefan; Delpierre, P.; Giudice, Pietro; Demaria, N.; Angelis, A. De; Beer, M. De; Boeck, H. De; Boer, W. De; Clercq, C. De; Laso, M.D.M. De Fez; Groot, N. De; Vaissière, Ch De La; Lotto, B. De; Min, A. De; Dijkstra, H.; Ciaccio, L. Di; Djama, F.; Dolbeau, J.; Dönszelmann, M.; Doroba, K.; Dracos, M.; Drees, J.; Dris, M.; Dufour, Y.; Eek, L. O.; Eerola, P.; Ehret, R.; Ekelöf, T.; Ekspong, G.; Peisert, A. Elliot; Engel, J. P.; Fassouliotis, D.; Feindt, M.; Alonso, M. Fernández; Ferrer, A.; Filippas, T. A.; Firestone, A.; Foeth, H.; Fokitis, E.; Fontanelli, F.; Forbes, K.A.J.; Fousset, J. L.; Francon, S.; Franek, B.; Frenkiel, P.; Fries, D. C.; Frodesen, A. G.; Frühwirth, R.; Fulda-Quenzer, F.; Furnival, K.; Fürstenau, H.; Fuster, J.; Galeazzi, G.; Gamba, D.; Garćıa, C.; Garcia, J. M. Vizan; Gaspar, C.; Gasparini, U.; Gavillet, Ph.; Gazis, E. N.; Gerber, J.; Giacomelli, P.; Gokieli, R.; Golob, B.; Golovatyuk, V.; Gomez, Y Cadenas J.J.; Goobar, A.; Gopal, G. P.; Górski, M.; Gracco, V.; Grant, A.; Grard, F.; Graziani, E.; Grosdidier, G.; Gross, E.; Grossetete, B.; Grosse‐Wiesmann, P.; Gumenyuk, S.; Guy, J.; Haedinger, U.; Hahn, F.; Hahn, M.; Haider, S.; Hajduk, Z.; Hakansson, A.; Hallgren, A.; Hamacher, K.; Monchenault, G. Hamel de; Hao, W.; Harris, F. J.; Henkes, T.; Hernández, J. J.; Herquet, P.; Herr, H.; Hessing, T. L.; Hietanen, I.; Higgins, C. O.; Higón, E.; Hilke, H. J.; Hodgson, S. D.; Hofmokl, T.; Holmes, R.; Holmgren, S. O.; Holthuizen, D.; Honoré, P. F.; Hooper, J. E.; Houlden, M.; Hrubec, J.; Huet, C.; Hulth, P. O.; Hultqvist, K.; Ioannou, P.; Isenhower, D.; Iversen, P. S.; Jackson, J. N.; Jałocha, P.; Jarlskog, G.; Jarry, P.; Jean‐Marie, B.; Johansson, Erik; Johnson, D.; Jonker, M.; Jönsson, L.; Juillot, P.; Kalkanis, G.; Kalkkinen, Jussi; Kalmus, G.; Kapusta, F.; Karlsson, M.; Karvelas, E.; Katsanevas, S.; Katsoufis, E.; Keränen, R.; Kesteman, J.; Khomenko, B. A.; Khovanski, N. N.; King, B. T.; Kjaer, N. J.; Klein, H.; Klempt, W.; Klovning, A.; Kluit, P.; Koch-Mehrin, A.; Köhne, J. H.; Koene, B.; Kokkinias, P.; Kopf, M.; Korcyl, K.; Korytov, A.; Kostukhin, V.; Kourkoumelis, C.; Kouznetsov, O.; Kramer, P.; Królikowski, J.; Kronkvist, I.; Krüner-Marquis, U.; Kucewicz, W.; Kulka, K.; Kurvinen, K.; Lacasta, C.; Lambropoulos, C.; Lämsä, J.; Lanceri, L.; Lapin, V.; Laugier, J. P.; Lauhakangas, R.; Leder, G.; Ledroit, F.; Leitner, R.; Lemoigne, Y.; Lemonne, J.; Lenzen, G.; Lepeltier, V.; Lesiak, T.; Lévy, J. M.; Lieb, E.; Liko, D.; Lindgren, J.; Lindner, R.; Lipniacka, A.; Lippi, I.; Lörstad, B.; Lokajı́ček, M.; Loken, J.; Lopez-Fernandez, A.; Aguera, M. A. Lopez; Los, M.; Loukas, D.; Lozano, J.; Lutz, P.; Lyons, L.; Mahlum, G.; Maillard, J.; Maltezos, A.; Mandl, F.; Marco, J.; Margoni, M.; Marin, J. C.; Μάρκου, Α.; Maron, T.; Martí, S.; Mathis, L.; Matorras, F.; Matteuzzi, C.; Matthiae, G.; Mazzucato, M.; McCubbin, M.; McKay, R.; McNulty, R.; Meola, G.; Meroni, C.; Meyer, W. T.; Michelotto, M.; Mikulec, I.; Mirabito, L.; Mitaroff, W.; Mitselmakher, G.; Mjörnmark, U.; Moa, T.; Möller, R.; Mönig, K.; Monge, M. R.; Morettini, P.; Müller, H.; Murray, W. J.; Myatt, G.; Naraghi, F.; Navarria, F. L.; Negri, P.; Nielsen, B. S.; Nijjhar, B.; Nikolaenko, V.; Nilsen, P.E.S.; Niss, P.; Obraztsov, V.; Olshevski, A. G.; Orava, R.; Ostankov, A.; Österberg, K.; Ouraou, A.; Paganoni, M.; Pain, R.; Pałka, H.; Papadopoulou, Th. D.; Pape, L.; Passeri, A.; Pegoraro, M.; Pennanen, J.; Perevozchikov, V.; Pernicka, M.; Perrotta, A.; Petridou, C.; Petrolini, A.; Petrovykh, L.P.; Pettersen, T.E.; Pierre, F.; Pimenta, M.; Pingot, O.; Plaszczynski, S.; Pol, M. E.; Polok, G.; Poropat, P.; Privitera, P.; Pullia, A.; Radojičić, D.; Ragazzi, S.; Rahmani, H.; Ratoff, P. N.; Read, A. L.; Redaelli, N.; Regler, M.; Reid, D.; Renton, P.; Resvanis, L. K.; Richard, F.; Richardson, M.; Řídký, J.; Rinaudo, G.; Roditi, I.; Romero, A.; Roncagliolo, I.; Ronchese, P.; Ronnqvist, C.; Rosenberg, E. I.; Rossi, S.; Rossi, U.; Rosso, E.; Roudeau, P.; Rovelli, T.; Ruckstuhl, W.; Ruhlmann-Kleider, V.; Ruiz, A.; Saarikko, H.; Sacquin, Y.; Sajot, G.; Salt, J.; Sánchez, J.; Sannino, M.; Schael, S.; Schneider, H.; Schulze, Bruno; Schyns, M. A E; Sciolla, G.; Scuri, F.; Segar, A. M.; Sekulin, R.; Sessa, M.; Sette, G.; Seufert, R.; Shellard, R. C.; Siccama, I.; Siegrist, P.; Simonetti, S.; Simonetto, F.; Sisakian, A. N.; Skaali, T. B.; Skjevling, G.; Smadja, G.; Smith, G. R.; Sosnowski, R.; Spassoff, T. S.; Spiriti, E.; Squarcia, S.; Stack, H.; Stănescu, C.; Stapnes, S.; Stavropoulos, G.; Stichelbaut, F.; Stocchi, A.; Strauss, J.; Straver, J.; Strub, R.; Szczekowski, M.; Szeptycka, M.; Szymański, P.; Tabarelli, T.; Tavernier, S.; Chikilev, O.; Theodosiou, G.; Tilquin, A.; Timmermans, J.; Timofeev, V. G.; Tkatchev, L. G.; Todorov, T.; Toet, D. Z.; Toker, O.; Torassa, E.; Tortora, L.; Treille, D.; Trevisan, U.; Tristram, G.; Troncon, C.; Tsirou, A.; Tsyganov, E. N.; Turluer, M. L.; Tuuva, T.; Tyapkin, I. A.; Tyndel, M.; Tzamarias, S.; Uberschar, S.; Ullaland, O.; Uvarov, V.; Valenti, G.; Vallazza, E.; Ferrer, J. A. Valls; Velde, C. Vander; Apeldoorn, G. W. van; Dam, P. Van; Heijden, M. van der; Doninck, W. K. Van; Vaz, P.; Vegni, G.; Ventura, L.; Vénus, W.; Verbeure, F.; Vertogradov, L. S.; Vilanova, D.; Vincent, P.; Vitale, L.; Vlasov, E.; Vodopyanov, A.; Vollmer, M.; Voulgaris, G.; Voutilainen, M.; Vrba, V.; Wahlen, H.; Walck, C.; Waldner, F.; Wayne, M.; Wehr, A.; Weierstall, M.; Weilhammer, P.; Werner, John S.; Wetherell, A. M.; Wickens, J.; Wikne, J.; Wilkinson, G.; Williams, W. S. C.; Winter, M.; Witek, M.; Wormald, D.; Wormser, G.; Woschnagg, K.; Yamdagni, N.; Yepes, P.; Zaitsev, A.; Zalewska, A.; Zalewski, P.; Zavrtanik, D.; Zevgolatakos, E.; Zhang, G.

doi:10.1016/0370-2693(92)91580-3

Cited by 45 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks have been applied to a wide variety of problems in high-energy physics [1,2], from event classification [3,4] to object reconstruction [5,6] and triggering [7,8]. Typically, however, these networks are applied to solve a specific isolated problem, even when this problem is part of a set of closely related problems.…”

Section: Introductionmentioning

confidence: 99%

Parameterized neural networks for high-energy physics

et al. 2016

View full text Add to dashboard Cite

We investigate a new structure for machine learning classifiers built with neural networks and applied to problems in high-energy physics by expanding the inputs to include not only measured features but also physics parameters. The physics parameters represent a smoothly varying learning task, and the resulting parameterized classifier can smoothly interpolate between them and replace sets of classifiers trained at individual values. This simplifies the training process and gives improved performance at intermediate values, even for complex problems requiring deep learning. Applications include tools parameterized in terms of theoretical model parameters, such as the mass of a particle, which allow for a single network to provide improved discrimination across a range of masses. This concept is simple to implement and allows for optimized interpolatable results.

show abstract

Section: Introductionmentioning

confidence: 99%

Parameterized neural networks for high-energy physics

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The best performance were obtained with about 500 trees and a minimum number of jets per leaf of about 7000. In order to implement the ANN, the Jetnet 3.0 package [13] was considered, since it has been broadly accepted and used in leading high energy physics experiments since the 1990's [2,3]. The architecture of the network consisted of 7 nodes in the input layer (corresponding to the 7 discriminating variables mentioned above), 14 (15) nodes in the hidden layer for the first (second) training step and 1 node in the output layer.…”

Section: Resultsmentioning

confidence: 99%

“…The tagging performance is substantially improved when individual taggers are combined to give a single jet classifier. In high energy physics, Fisher discriminants [1] and artificial neural networks (ANN) [2] are the most popular methods for combining several discriminating variables into one classifier, and have been extensively applied to b-tagging [3]. Boosted decision trees (BDT) is a newly developed learning technique [4] that was recently introduced to high energy experimentalists by the MiniBooNE Particle ID group [5].…”

Section: Introductionmentioning

confidence: 99%

A multivariate approach to heavy flavour tagging with cascade training

Bastos

Liu

2007

J. Inst.

View full text Add to dashboard Cite

This paper compares the performance of artificial neural networks and boosted decision trees, with and without cascade training, for tagging b-jets in a collider experiment. It is shown, using a Monte Carlo simulation of W H → lνqq events, that for a b-tagging efficiency of 50%, the light jet rejection power given by boosted decision trees without cascade training is about 55% higher than that given by artificial neural networks. The cascade training technique can improve the performance of boosted decision trees and artificial neural networks at this b-tagging efficiency level by about 35% and 80% respectively. We conclude that the cascade trained boosted decision trees method is the most promising technique for tagging heavy flavours at collider experiments.

show abstract

“…using boosted decision trees (BDTs) on calculated features for doing ID classification and energy regression. Indeed, ML has long been applied to various tasks in HEP [1][2][3], but has recently seen much wider application [4][5][6][7][8][9], including the 2012 discovery of the Higgs boson [10,11] at the ATLAS [12] and CMS [13] experiments at the Large Hadron Collider (LHC).…”

Section: Overviewmentioning

confidence: 99%

Calorimetry with deep learning: particle simulation and reconstruction for collider physics

et al. 2020

View full text Add to dashboard Cite

Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of single isolated particles produced in high-energy physics collisions. We train neural networks on single-particle shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.

show abstract

Classification of the hadronic decays of the Z0 into b and c quark pairs using a neural network

Cited by 45 publications

References 14 publications

Parameterized neural networks for high-energy physics

Parameterized neural networks for high-energy physics

A multivariate approach to heavy flavour tagging with cascade training

Calorimetry with deep learning: particle simulation and reconstruction for collider physics

Contact Info

Product

Resources

About