Deep learning in color: towards automated quark/gluon jet discrimination

By Patrick T. Komiske, E. Metodiev, M. Schwartz. 2016

279 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Nuclear and High Energy Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Nuclear and High Energy Physics

Citations in the corpus

Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis (2017, methodology): “udinal segmentation (e.g. the CMS detector [25]). Adding layers, either through longitudinal segmentation or combining information from multiple detectors, has recently been studied for classication [22] and generation [26], but is beyond the scope of this paper. Jet images are constructed and pre-p”
The Lund jet plane (2018, methodology): “ing a batch size of 128, with Adam as optimisation algorithm [78] and a categorical cross-entropy loss function. The parameters for the machine learning are similar, where relevant, to those in Refs. [37,38], though we used a greater number of pixels for the images and larger networks. Training is c”
Energy flow networks: deep sets for particle jets (2018, methodology): “parable classication performance with similar information. The other machine learning architectures we compare to are a DNN trained on the Nsubjettiness basis [23,67,68], a CNN trained on jet images [4,5,8], and a linear classier trained on the energy ow basis [28]. Their performance, as given by th”
QCD-aware recursive neural networks for jet physics (2017, background): “[7], but we did not observe any significant gains in classification performance with respect to the towers scenario.”
Energy flow polynomials: a complete linear basis for jet substructure (2017, methodology): “Jet images have been applied successfully to the same tagging problems considered here: quark/gluon discrimination [65], W tagging [63], and top tagging [66, 68].”
JUNIPR: a framework for unsupervised machine learning in particle physics (2018, methodology): “and they generally outperform fully-connected networks due to their ecient feature detection. In the rst applications of CNNs to jet images, on boosted Wdetection [20] and quark/gluon discrimination [21], it was indeed found that simple CNNs could generally outperform previous techniques. Since then”
Jet substructure at the Large Hadron Collider (2018, unknown): “discrimination power [133].”
A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists (2017, background): “…organizing collider data as images (called jet images), scientists found CNNs to be successful in identifying diverse particles (Aurisano et al., 2016; Butter et al., 2017; de Oliveira et al., 2016; Komiske et al., 2017; Racah et al., 2016) and classifying physical events (Racah et al., 2016).”
Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learning (2017, background): “Grayscale images were expanded to include additional layers (‘colors’) to encode more information such as charge-energy versus neutral-energy [494].”
A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends (2018, background): “[69] tested CNNs for discriminating quark and gluon jet deposits in comparison with traditional observables designed by physicists.”