Pulling out all the tops with computer vision and deep learning

Macaluso, Sebastian; Shih, David

doi:10.1007/jhep10(2018)121

Cited by 163 publications

(178 citation statements)

References 76 publications

(112 reference statements)

Supporting

Mentioning

178

Contrasting

Order By: Relevance

“…These are of the general form of IRC-safe angularities [74] with a generic radially-symmetric angular weighting function [85]. 12 To quantify the filters further, in Fig. 13c we plot the value of the learned filters as a function of the radial distance, taking an envelope over several radial slices.…”

Section: Extracting New Observables From the Modelmentioning

confidence: 99%

Energy flow networks: deep sets for particle jets

Komiske

Metodiev

Thaler

2019

J. High Energ. Phys.

266

284

View full text Add to dashboard Cite

A key question for machine learning approaches in particle physics is how to best represent and learn from collider events. As an event is intrinsically a variablelength unordered set of particles, we build upon recent machine learning efforts to learn directly from sets of features or "point clouds". Adapting and specializing the "Deep Sets" framework to particle physics, we introduce Energy Flow Networks, which respect infrared and collinear safety by construction. We also develop Particle Flow Networks, which allow for general energy dependence and the inclusion of additional particle-level information such as charge and flavor. These networks feature a per-particle internal (latent) representation, and summing over all particles yields an overall event-level latent representation. We show how this latent space decomposition unifies existing event representations based on detector images and radiation moments. To demonstrate the power and simplicity of this set-based approach, we apply these networks to the collider task of discriminating quark jets from gluon jets, finding similar or improved performance compared to existing methods. We also show how the learned event representation can be directly visualized, providing insight into the inner workings of the model. These architectures lend themselves to efficiently processing and analyzing events for a wide variety of tasks at the Large Hadron Collider. Implementations and examples of our architectures are available online in our EnergyFlow package.

show abstract

Section: Extracting New Observables From the Modelmentioning

confidence: 99%

Energy flow networks: deep sets for particle jets

Komiske

Metodiev

Thaler

2019

J. High Energ. Phys.

266

284

View full text Add to dashboard Cite

show abstract

“…The top jets are truth-matched, and the images include the improved pre-processing taken from Ref. [9]. The constituents for the LoLa tagger are extracted through the Delphes energyflow algorithm, and the 4-momenta of the leading 200 constituents are stored.…”

Section: Performancementioning

confidence: 99%

Deep-learning jets with uncertainties and more

et al. 2020

View full text Add to dashboard Cite

Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning taggers. We show how they capture statistical uncertainties from finite training samples, systematics related to the jet energy scale, and stability issues through pile-up. Altogether, Bayesian networks offer many new handles to understand and control deep learning at the LHC without introducing a visible prior effect and without compromising the network performance. Content

show abstract

“…To improve the performance of our taggers, we preprocess each image, following a similar procedure as in ref. [16]: centralization, rotation and flipping. In figures 3 and 4, we use φ and η to denote the new coordinate system for the images after preprocessing.…”

Section: Jet Imagesmentioning

confidence: 99%

Boosted W and Z tagging with jet charge and deep learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

We demonstrate that the classification of boosted, hadronically-decaying weak gauge bosons can be significantly improved over traditional cut-based and BDTbased methods using deep learning and the jet charge variable. We construct binary taggers for W + vs. W − and Z vs. W discrimination, as well as an overall ternary classifier for W + /W − /Z discrimination. Besides a simple convolutional neural network (CNN), we also explore a composite of two CNNs, with different numbers of layers in the jet p T and jet charge channels. We find that this novel structure boosts the performance particularly when considering the Z boson as signal. The methods presented here can enhance the physics potential in SM measurements and searches for new physics that are sensitive to the electric charge of weak gauge bosons. arXiv:1908.08256v1 [hep-ph] 22 Aug 2019 1 We have also studied the scenario where m H5 = 2 TeV that leads to p T of each boson around 1 TeV, and found all results qualitatively the same.

show abstract

Pulling out all the tops with computer vision and deep learning

Cited by 163 publications

References 76 publications

Energy flow networks: deep sets for particle jets

Energy flow networks: deep sets for particle jets

Deep-learning jets with uncertainties and more

Boosted W and Z tagging with jet charge and deep learning

Contact Info

Product

Resources

About