Topology Classification with Deep Learning to Improve Real-Time Event Selection at the LHC

@article{Nguyen2019TopologyCW,
  title={Topology Classification with Deep Learning to Improve Real-Time Event Selection at the LHC},
  author={Thong Q. Nguyen and Daniel Weitekamp and Dustin Anderson and Roberto Castello and Olmo Cerri and Maurizio Pierini and Maria Spiropulu and J. R. Vlimant},
  journal={Computing and Software for Big Science},
  year={2019},
  volume={3},
  pages={1-14}
}
We show how an event topology classification based on deep learning could be used to improve the purity of data samples selected in real time at the Large Hadron Collider. We consider different data representations, on which different kinds of multi-class classifiers are trained. Both raw data and high-level features are utilized. In the considered examples, a filter based on the classifier’s score can be trained to retain $$\sim 99\%$$∼99% of the interesting events and reduce the false… 

Variational autoencoders for new physics mining at the Large Hadron Collider

TLDR
A one-sided threshold test to isolate previously unseen processes as outlier events is developed, which could inspire new-physics model building and new experimental searches, and be complementary to classic LHC searches.

Machine Learning Solutions for High Energy Physics: Applications to Electromagnetic Shower Generation, Flavor Tagging, and the Search for di-Higgs Production

TLDR
The notion of ML powering particle physics in the upcoming years is substantiate by bridging the gap between ML and particle physics and establishing baselines for future applications.

Autoencoders on field-programmable gate arrays for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider

TLDR
This work shows how to adapt and deploy deep-learning-based autoencoders for the unsupervised detection of new physics signatures in the challenging environment of a real-time event selection system at the Large Hadron Collider, and enables the practical deployment of these networks during the next data-taking campaign of the Large hadron Collider.

Searching for new physics with deep autoencoders

TLDR
A potentially powerful new method of searching for new physics at the LHC, using autoencoders and unsupervised deep learning, which opens up the exciting possibility of training directly on actual data to discover new physics with no prior expectations or theory prejudice.

Application of a Convolutional Neural Network for image classification to the analysis of collisions in High Energy Physics

TLDR
An intuitive approach to transform physical variables, like momenta of particles and jets, into a single image that captures the relevant information, is proposed and shows competitive results when compared to more classical approaches, like those using feedforward neural networks.

Automating the ABCD method with machine learning

TLDR
Automating the ABCD method with machine learning significantly improves performance in terms of ABCD closure, background rejection and signal contamination, and uncovers a previously unappreciated aspect of the method: its accuracy hinges on having low signal contamination in control regions not just overall, but relative to the signal fraction in the signal region.

FPGA-Accelerated Machine Learning Inference as a Service for Particle Physics Computing

TLDR
It is demonstrated that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model.

Learning representations of irregular particle-detector geometry with distance-weighted graph networks

TLDR
The proposed algorithms provide an interesting alternative to existing methods, offering equally performing or less resource-demanding solutions with less underlying assumptions on the detector geometry and, consequently, the possibility to generalize to other detectors.

Machine Learning Pipelines with Modern Big Data Tools for High Energy Physics

TLDR
A solution to these challenges is presented, which allows training neural network classifiers using solutions from the Big Data and data science ecosystems, integrated with tools, software, and platforms common in the HEP environment.

Fast convolutional neural networks for identifying long-lived particles in a high-granularity calorimeter

TLDR
It is shown that a simple convolutional neural network, that could in principle be deployed on dedicated fast hardware, can efficiently identify showers from displaced particles down to low energies while providing a low trigger rate.

References

SHOWING 1-10 OF 42 REFERENCES

Jet flavor classification in high-energy physics with deep neural networks

TLDR
This work finds that the highest-level lowest-dimensionality expert information sacrifices information needed for classification, that the performance of current state-of-the-art taggers can be matched or slightly exceeded by deep-network-based taggers using only track and vertex information, and that classification using only lowest-level highest- dimensionality tracking information remains a difficult task for deep networks.

Deep Neural Networks for Physics Analysis on low-level whole-detector data at the LHC

TLDR
This work uses an existing RPV-Supersymmetry analysis as a case study and explores CNNs on multi-channel, high-resolution sparse images: applied on GPU and multi-node CPU architectures on the Cori supercomputer at NERSC.

Searching for exotic particles in high-energy physics with deep learning.

TLDR
It is shown that deep-learning methods need no manually constructed inputs and yet improve the classification metric by as much as 8% over the best current approaches, demonstrating that deep learning approaches can improve the power of collider searches for exotic particles.

Recursive Neural Networks in Quark/Gluon Tagging

  • Taoli Cheng
  • Computer Science
    Computing and Software for Big Science
  • 2018
TLDR
The results show that RecNNs work better than the baseline boosted decision tree (BDT) by a few percent in gluon rejection rate, however, extra implementation of particle flow identification only increases the performance slightly.

Real Time Data Analysis With the ATLAS Trigger at the LHC in Run-2

The trigger selection capabilities of the ATLAS detector have been significantly enhanced for the Large Hadron Collider (LHC) Run-2 in order to cope with the higher event rates and with a large

Application of a Convolutional Neural Network for image classification to the analysis of collisions in High Energy Physics

TLDR
An intuitive approach to transform physical variables, like momenta of particles and jets, into a single image that captures the relevant information, is proposed and shows competitive results when compared to more classical approaches, like those using feedforward neural networks.

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

A bstractArtificial 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

Boosted Decision Trees in the Level-1 Muon Endcap Trigger at CMS

TLDR
The first implementation of a Machine Learning Algorithm inside a Level-1 trigger system at the LHC is presented and the new momentum algorithm reduced the background rate by a factor of three with respect to the previous analytic algorithm.

LHCb Topological Trigger Reoptimization

TLDR
It is demonstrated that the reoptimized topological trigger is expected to significantly improve on the Run 1 performance for a wide range of b-hadron decays.

Image Processing, Computer Vision, and Deep Learning: new approaches to the analysis and physics interpretation of LHC events

TLDR
It is shown that state-of-the-art image classification techniques based on deep neural network architectures significantly improve the identification of highly boosted electroweak particles with respect to existing methods.