Deep learning in color: towards automated quark/gluon jet discrimination
Artificial intelligence offers the potential to automate challenging data-processing tasks in collider physics. To establish its prospects, we explore to what extent deep learning with convolutional neural networks can discriminate quark and gluon jets better than observables designed by physicists. Our approach builds upon the paradigm that a jet can be treated as an image, with intensity given by the local calorimeter deposits. We supplement this construction by adding color to the images, with red, green and blue intensities given by the transverse momentum in charged particles, transverse momentum in neutral particles, and pixel-level charged particle counts. Overall, the deep networks match or outperform traditional jet variables. We also find that, while various simulations produce different quark and gluon jets, the neural networks are surprisingly insensitive to these differences, similar to traditional observables. This suggests that the networks can extract robust physical information from imperfect simulations.
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.
- A. Krizhevsky, I. Sutskever and G.E. Hinton, Imagenet classification with deep convolutional neural networks, in the proceedings of Neural Information Processing Systems (NIPS 2012), December 3-8, Lake Tahoe, U.S.A. (2012).Google Scholar
- OPAL collaboration, A Study of differences between quark and gluon jets using vertex tagging of quark jets, Z. Phys. C 58 (1993) 387.Google Scholar
- OPAL collaboration, A direct observation of quark-gluon jet differences at LEP, Phys. Lett. B 265 (1991) 462.Google Scholar
- R. Collobert and J. Weston, A unified architecture for natural language processing: deep neural networks with multitask learning, in the proceedings of the 25th International Conference on Machine Learning, July 5-9, Helsinki, Finland (2008).Google Scholar
- M.A. Nielsen, Neural networks and deep learning, Determination Press, U.S.A. (2015).Google Scholar
- I. Goodfellow, Y. Bengio and A. Courville, Deep learning, MIT Press, U.S.A. (2016).Google Scholar
- X. Glorot, A. Bordes and Y. Bengio, Deep sparse rectifier neural networks, in the proceedings of the 14th International Conference on Artificial Intelligence and Statistics, April 11-13, Ft. Lauderdale, U.S.A. (2011).Google Scholar
- C. Szegedy et al., Going deeper with convolutions, in the proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 7-12, Boston U.S.A. (2015), arXiv:1409.4842.
- P.Y. Simard, D. Steinkraus and J.C. Platt, Best practices for convolutional neural networks applied to visual document analysis, ICDAR 3 (2003).Google Scholar
- F. Chollet, Keras, available at GitHub (2015).
- J. Bergstra et al., Theano: a CPU and GPU math compiler in Python, in the proceedings of the 9th Python in science conference, June 28-July 3, Austin, U.S.A. (2010).Google Scholar
- K. He, X. Zhang, S. Ren and J. Sun, Delving deep into rectifiers: surpassing human-level performance on imagenet classification, in the proceedings of the IEEE International Conference on Computer Vision, December 11-18, Santiago, Chile (2015).Google Scholar
- D. Kingma and J. Ba, Adam: a method for stochastic optimization, arXiv:1412.6980.
- J. Snoek, H. Larochelle and R.P. Adams, Practical bayesian optimization of machine learning algorithms, in the proceedings of Neural Information Processing Systems (NIPS 2012), December 3-8, Lake Tahoe, U.S.A. (2012), arXiv:1206.2944.
- CMS Collaboration, Particle-flow event reconstruction in CMS and Performance for Jets, Taus and MET, CMS-PAS-PFT-09-001 (2009).
- H. Küçük, Measurement of the inclusive-jet cross-section in proton-proton collisions and study of quark-gluon jet discrimination with the ATLAS experiment at the LHC, Dissertation, University College London, London. U.K. (2016).Google Scholar