Abstract
We present a study to optimize multi-layer perceptron (MLP) classification power with a Rocks Linux cluster [1]. Simulated data from a future high energy physics experiment at the Large Hadron Collider (LHC) is used to teach a neural network to separate the Higgs particle signal from a dominant background [2].
The MLP classifiers have been implemented using the ROOT data analysis framework [3]. Our aim is to reach a stable physics signal recognition for new physics and a well understood background rejection. We report on the physics performance of new neural classifiers developed in this study. We have used the benchmarking capabilities of ROOT and of the Parallel ROOT facility (PROOF) [4] to compare the performance of the Linux clusters at our campus.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Heikkinen, A., Lindén, T.: Validation of GEANT4 Bertini cascade nuclide production using parallel Root facility. In: Proc. of Computing in High Energy and Nuclear Physics, February 13–17, 2006, Mumbai, India (in press, 2006)
Heikkinen, A., Lehti, S.: Tagging b jets associated with heavy neutral MSSM Higgs bosons. NIM A 559, 195–198 (2006)
Rademakers, F., Goto, M., Canal, P., Brun, R.: ROOT Status and Future Developments. arXiv: cs.SE/0306078, http://root.cern.ch/
Ganis, G., et al.: PROOF – The Parallel ROOT Facility. In: Proc. of Computing in High Energy and Nuclear Physics 2006, 13 – 17 February 2006, Mumbai, India (In press)
Lehti, S.: Tagging b-Jets in bb H SUSY →ττ. CMS NOTE 2001/019
Weiser, C.: A Combined Secondary Vertex Based B-Tagging Algorithm in CMS. CMS NOTE 2006/014
Lehti, S.: Study of MSSM H/A→ττ→eμ + X in CMS. CMS NOTE 2006/101
Kinnunen, R., Lehti, S.: Search for the heavy neutral MSSM Higgs bosons with the H/A→τ + τ − → electron + jet decay mode. CMS NOTE 2006/075
Sjostrand, T., Lönnblad, L., Mrenna, S.: PYTHIA 6.2 Physics and Manual, hep-ph/010826, LU TP 01/21, 3rd edn. (April 2003)
Lai, H.L., Huston, J., Kuhlmann, S., Morfin, J., Olness, F., Owens, J.F., Pumplin, J., Tung, W.K.: Global QCD Analysis of Parton Structure of the Nucleon: CTEQ5 Parton Distributions, hep-ph/9903282. Eur. Phys. J. C12, 375–392 (2000)
ORCA, Object-oriented Reconstruction for CMS Analysis, http://cmsdoc.cern.ch/orca
CMS Collaboration: Data Acquisition & High-Level Trigger Technical Design Report, CERN/LHCC 2002-26, CMS TDR 6.2 (December 2002)
Chekanov, S.V.: Jet algorithms: A mini review, hep-ph/0211298
Adam, W., Mangano, B., Speer, Th., Todorov, T.: Track reconstruction in the CMS tracker, CMS NOTE 2006/041
Papadopoulos, P., Katz, M., Bruno, G.: NPACI Rocks: Tools and Techniques for Easily Deploying Manageable Linux Clusters. Concurrency Computat: Pract. Exper. 00. 1–20 (2002)
The list of the 500 fastest computers according to the Linpack benchmark, http://www.top500.org/
The homepage of NPACI Rocks cluster distribution, http://www.rocksclusters.org/
Segneri, G., Palla, F.: Lifetime based b-tagging with CMS. CMS NOTE 2002/046
Caballero, I.G., Cano, D., Marco, R., Cuevas, J.: Prototype of a parallel analysis system for CMS using PROOF. In: Proc. of Computing in High Energy and Nuclear Physics, February 13-17, 2006, Mumbai, India (in press)
The Twiki page of PROOF, http://root.cern.ch/twiki/bin/view/ROOT/PROOF
The home page of xrootd, http://xrootd.slac.stanford.edu
Ballintijn, M., Roland, G., Gulbrandsen, K., Brun, R., Rademakers, F., Canal, P.: Super scaling PROOF to very large clusters. In: Proc. of Computing in High Energy and Nuclear Physics 2004, September 27 - October 1, 2004, Interlaken, Switzerland, CERN-2005-002, vol. 1 (2005)
Tentindo-Repond, S., Prosper, H.B., Bhat, P.C.: Neural Networks for Higgs Physics. In: Proceedings of Advanced Computing and Analysis Techniques in Physics Research, VII International Workshop ACAT 2000, Batavia, Illinois (2000)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lindén, T., García, F., Heikkinen, A., Lehti, S. (2007). Optimizing Neural Network Classifiers with ROOT on a Rocks Linux Cluster. In: Kågström, B., Elmroth, E., Dongarra, J., Waśniewski, J. (eds) Applied Parallel Computing. State of the Art in Scientific Computing. PARA 2006. Lecture Notes in Computer Science, vol 4699. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75755-9_124
Download citation
DOI: https://doi.org/10.1007/978-3-540-75755-9_124
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75754-2
Online ISBN: 978-3-540-75755-9
eBook Packages: Computer ScienceComputer Science (R0)