Deep Learning and its Application to LHC Physics

Abstract

Machine learning has played an important role in the analysis of high-energy physics data for decades. The emergence of deep learning in 2012 allowed for machine learning tools which could adeptly handle higher-dimensional and more complex problems than previously feasible. This review is aimed at the reader who is familiar with high energy physics but not machine learning. The connections between machine learning and high energy physics data analysis are explored, followed by an introduction to the core concepts of neural networks, examples of the key results demonstrating the power of deep learning for analysis of LHC data, and discussion of future prospects and concerns.

Posted with permission from the Annual Review of Nuclear and Particle Science, Volume 68. (c) 2018 by Annual Reviews, http://www.annualreviews.org

References in corpus (21)

• Deep Learning in Neural Networks: An Overview
• PYTHIA 6.4 Physics and Manual
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• Improving neural networks by preventing co-adaptation of feature detectors
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Event generation with SHERPA 1.1
• Herwig++ Physics and Manual
• NICE: Non-linear Independent Components Estimation
• Particle-flow reconstruction and global event description with the CMS detector
• Observation of the diphoton decay of the Higgs boson and measurement of its properties
• Classification without labels: Learning from mixed samples in high energy physics
• Edward: A library for probabilistic modeling, inference, and criticism
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• A neural network clustering algorithm for the ATLAS silicon pixel detector
• RECAST: Extending the Impact of Existing Analyses
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• Modeling Smooth Backgrounds and Generic Localized Signals with Gaussian Processes
• Yadage and Packtivity - analysis preservation using parametrized workflows
• Arrays of (locality-sensitive) Count Estimators (ACE): High-Speed Anomaly Detection via Cache Lookups
• Machine learning and parallelism in the reconstruction of LHCb and its upgrade

Cited by in corpus (179)

• Machine learning and the physical sciences
• Searching for New Physics with Deep Autoencoders
• Machine Learning in Nuclear Physics
• Energy Flow Networks: Deep Sets for Particle Jets
• Graph Neural Networks in Particle Physics
• Simulation Assisted Likelihood-free Anomaly Detection
• Mining for Gluon Saturation at Colliders
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Quantum Machine Learning in High Energy Physics
• Higgs boson production cross-section measurements and their EFT interpretation in the $4\ell$ decay channel at $\sqrt{s}$ = 13 TeV with the ATLAS detector
• Autoencoders for unsupervised anomaly detection in high energy physics
• Heavy Neutrinos with Dynamic Jet Vetoes: Multilepton Searches at $\sqrt{s}=14,27,$ and $100$ TeV
• Application of Quantum Machine Learning using the Quantum Kernel Algorithm on High Energy Physics Analysis at the LHC
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• Fast inference of Boosted Decision Trees in FPGAs for particle physics
• Spectral Reconstruction with Deep Neural Networks
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• Searches for the BSM scenarios at the LHC using decision tree based machine learning algorithms: A comparative study and review of Random Forest, Adaboost, XGboost and LightGBM frameworks
• Convergence of Artificial Intelligence and High Performance Computing on NSF-supported Cyberinfrastructure
• Partial success in closing the gap between human and machine vision
• ABCDisCo: Automating the ABCD Method with Machine Learning
• A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Uncertainty Aware Learning for High Energy Physics
• Casting a graph net to catch dark showers
• Learning the latent structure of collider events
• Mapping Machine-Learned Physics into a Human-Readable Space
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• Novel approaches in Hadron Spectroscopy
• FAIR principles for AI models with a practical application for accelerated high energy diffraction microscopy
• Vertex and Energy Reconstruction in JUNO with Machine Learning Methods
• Transferability of Deep Learning Models in Searches for New Physics at Colliders
• Stochastic normalizing flows as non-equilibrium transformations
• Unsupervised Outlier Detection in Heavy-Ion Collisions
• Adaptable Hamiltonian neural networks
• Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data
• A fast centrality-meter for heavy-ion collisions at the CBM experiment
• Unravelling physics beyond the standard model with classical and quantum anomaly detection
• E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
• The Boosted Higgs Jet Reconstruction via Graph Neural Network
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Boosted decision trees in the era of new physics: a smuon analysis case study
• Mass Agnostic Jet Taggers
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Quantum Machine Learning for $b$-jet charge identification
• Event reconstruction for KM3NeT/ORCA using convolutional neural networks
• A Cautionary Tale of Decorrelating Theory Uncertainties
• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• Interpretable machine learning in Physics
• Higgs boson tagging with the Lund jet plane
• Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning
• Revealing the nature of hidden charm pentaquarks with machine learning
• Lorentz group equivariant autoencoders
• Higgs self-coupling measurements using deep learning in the $b\bar{b}b\bar{b}$ final state
• Triggering on Emerging Jets
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Inference of the Mass Composition of Cosmic Rays with energies from $10^{18.5}$ to $10^{20}$ eV using the Pierre Auger Observatory and Deep Learning
• An equation-of-state-meter for CBM using PointNet
• Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment
• Hybrid Quantum-Classical Graph Convolutional Network
• Power-law Scaling to Assist with Key Challenges in Artificial Intelligence
• Precision SMEFT bounds from the VBF Higgs at high transverse momentum
• Linear Frequency Principle Model to Understand the Absence of Overfitting in Neural Networks
• The Higgs boson Turns Ten
• Disentangling Boosted Higgs Boson Production Modes with Machine Learning
• Leveraging universality of jet taggers through transfer learning
• Invisible Higgs search through Vector Boson Fusion: A deep learning approach
• Covariantizing Phase Space
• Reconstructing boosted Higgs jets from event image segmentation
• GPU coprocessors as a service for deep learning inference in high energy physics
• A neural network classifier for electron identification on the DAMPE experiment
• Universal Relations in Composite Higgs Models
• Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources
• The Neutron Star Outer Crust Equation of State: A Machine Learning approach
• How Much Can We Really Trust You? Towards Simple, Interpretable Trust Quantification Metrics for Deep Neural Networks
• Particle Convolution for High Energy Physics
• Deep Learning Jet Image as a Probe of Light Higgsino Dark Matter at the LHC
• Random matrix analysis of deep neural network weight matrices
• From the Bottom to the Top -- Reconstruction of $t\bar{t}$ Events with Deep Learning
• Fitting a Collider in a Quantum Computer: Tackling the Challenges of Quantum Machine Learning for Big Datasets
• Quantum Vision Transformers for Quark-Gluon Classification
• Machine learning of log-likelihood functions in global analysis of parton distributions
• Boosted Ensembles of Qubit and Continuous Variable Quantum Support Vector Machines for B Meson Flavour Tagging
• Non-Parametric Data-Driven Background Modelling using Conditional Probabilities
• A method for approximating optimal statistical significances with machine-learned likelihoods
• Imaging particle collision data for event classification using machine learning
• Enhancing searches for resonances with machine learning and moment decomposition
• On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use case
• Neural network--featured timing systems for radiation detectors: performance evaluation based on bound analysis
• Supporting High-Performance and High-Throughput Computing for Experimental Science
• Fast convolutional neural networks for identifying long-lived particles in a high-granularity calorimeter
• The particle track reconstruction based on deep learning neural networks
• A tagger for strange jets based on tracking information using long short-term memory
• Application of Graph Networks to background rejection in Imaging Air Cherenkov Telescopes
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• Rapid identification of time-frequency domain gravitational wave signals from binary black holes using deep learning
• Learning Tree Structures from Leaves For Particle Decay Reconstruction
• Machine-learning approach to finite-size effects in systems with strongly interacting fermions
• Realizing the potential of deep neural network for analyzing neutron star observables and dense matter equation of state
• Guided Quantum Compression for High Dimensional Data Classification
• Towards a method to anticipate dark matter signals with deep learning at the LHC
• Deconstructing experimental decay energy spectra: the ${}^{26}$O case
• Energy reconstruction for large liquid scintillator detectors with machine learning techniques: aggregated features approach
• Beyond $M_{t\bar{t}}$: learning to search for a broad $t\bar{t}$ resonance at the LHC
• Deep Neural Network application: Higgs boson CP state mixing angle in H to tau tau decay and at LHC
• Class Imbalance Techniques for High Energy Physics
• Accuracy versus precision in boosted top tagging with the ATLAS detector
• Probing Higgs exotic decay at the LHC with machine learning
• Beyond Cuts in Small Signal Scenarios -- Enhanced Sneutrino Detectability Using Machine Learning
• Using Machine Learning to Improve Neutron Identification in Water Cherenkov Detectors
• Perspectives and Outlook from HEP Window on the Universe
• Meta-learning and data augmentation for mass-generalised jet taggers
• Deep Learning-Based Spatiotemporal Multi-Event Reconstruction for Delay Line Detectors
• Development of a Vertex Finding Algorithm using Recurrent Neural Network
• Search for single vector-like $B$ quark production in hadronic final states at the LHC
• Machine learning classification: case of Higgs boson CP state in H to tau tau decay at LHC
• Resolving Combinatorial Ambiguities in Dilepton $t\bar{t}$ Event Topologies with Neural Networks
• Enhancing Cosmological Model Selection with Interpretable Machine Learning
• Automatic detection of boosted Higgs boson and top quark jets in an event image
• Portable acceleration of CMS computing workflows with coprocessors as a service
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
• Deep Neural Networks to Recover Unknown Physical Parameters from Oscillating Time Series
• Semi-supervised learning combining backpropagation and STDP: STDP enhances learning by backpropagation with a small amount of labeled data in a spiking neural network
• Les Houches guide to reusable ML models in LHC analyses
• Machine-Learning Performance on Higgs-Pair Production Associated with Dark Matter at the LHC
• Inferring Hidden Symmetries of Exotic Magnets from Detecting Explicit Order Parameters
• Influence of QCD parton shower in deep learning invisible Higgs through vector boson fusion
• Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting
• Insights into Dark Matter Direct Detection Experiments: Decision Trees versus Deep Learning
• Calculating Pull for Non-Singlet Jets
• Reconstructing axion-like particles from beam dumps with simulation-based inference
• Artificial intelligence for improved fitting of trajectories of elementary particles in inhomogeneous dense materials immersed in a magnetic field
• Neural networks for boosted di-$\tau$ identification
• A Data-Driven Machine Learning Approach for Electron-Molecule Ionization Cross Sections
• PAIReD jet: A multi-pronged resonance tagging strategy across all Lorentz boosts
• Classifier Surrogates: Sharing AI-based Searches with the World
• Unifying supervised learning and VAEs -- coverage, systematics and goodness-of-fit in normalizing-flow based neural network models for astro-particle reconstructions
• Discriminating sub-TeV gamma and hadron-induced showers through their footprints
• Fast multilabel classification of HEP constraints with deep learning
• Machine-Learning Analysis of Radiative Decays to Dark Matter at the LHC
• Boundary between noise and information applied to filtering neural network weight matrices
• Jet energy calibration with deep learning as a Kubeflow pipeline
• Machine-learning-based prediction of parameters of secondaries in hadronic showers using calorimetric observables
• Exploring the Universality of Hadronic Jet Classification
• The use of Boosted Decision Trees for Energy Reconstruction in JUNO experiment
• Renormalization-group-inspired neural networks for computing topological invariants
• Safety of Quark/Gluon Jet Classification
• Predicting the Masses of Exotic Hadrons with Data Augmentation Using Multilayer Perceptron
• Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection
• Applicability Evaluation of Selected xAI Methods for Machine Learning Algorithms for Signal Parameters Extraction
• PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction
• Search for anomalous quartic gauge couplings in the process ${\mu }^{+}{\mu }^{-}\to \bar{\nu }\nu \gamma \gamma$ with a nested local outlier factor
• Information Condensing Active Learning
• Machine learning approach for the search of resonances with topological features at the Large Hadron Collider
• Machine learning of the well known things
• A quantum machine learning classifier to search for new physics
• Systematically Constructing the Likelihood for Boosted $H\to gg$ Decays
• Neural Scaling Laws for Deep Regression
• Suppression of accidental backgrounds with deep neural networks in the PandaX-II experiment
• Introduction and analysis of a method for the investigation of QCD-like tree data
• Jet Reconstruction with Mamba Networks in Collider Events
• Searching for top-philic heavy resonances in boosted four-top final states
• Detecting New Physics as Novelty -- Complementarity Matters
• Physics-informed neural network (PINN) modeling of charged particle multiplicity using the two-component framework in heavy-ion collisions: A comparison with data-driven neural networks
• Reweighting and Analysing Event Generator Systematics by Neural Networks on High-Level Features
• Shedding Light on Dark Matter at the LHC with Machine Learning
• Using holistic event information in the trigger
• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction
• Extraction of the color dipole amplitude with physics-informed neural networks
• Optimal event selection and categorization in high energy physics, Part 1: Signal discovery
• Neutral pion reconstruction using machine learning in the MINERvA experiment at $⟨E_{\nu }⟩\sim 6$ GeV
• Graph Reinforcement Learning for Exploring BSM Model Spaces
• Detection of collinear high energetic di-photon signatures with Micromegas Detectors
• Boosted and semi-boosted all-hadronic $t\bar{t}$ reconstruction performance on kinematic variables for selected BSM models using a 2D extesion of the BumpHunter algorithm
• Another Unorthodox Introduction to QCD and now Machine Learning
• Potential and limitations of machine-learning approaches to inclusive $|V_{ub}|$ determinations
• Top squark signal significance enhancement by different Machine Learning Algorithms
• Quantum Chebyshev Probabilistic Models for Fragmentation Functions