scispace - formally typeset
Search or ask a question
Posted Content

Novel deep learning methods for track reconstruction

TL;DR: Two sets of new deep learning models for reconstructing tracks using space-point data arranged as sequences or connected graphs that are scaleable with simple architecture and relatively few parameters are shown.
Abstract: Author(s): Farrell, Steven; Calafiura, Paolo; Mudigonda, Mayur; Prabhat; Anderson, Dustin; Vlimant, Jean-Roch; Zheng, Stephan; Bendavid, Josh; Spiropulu, Maria; Cerati, Giuseppe; Gray, Lindsey; Kowalkowski, Jim; Spentzouris, Panagiotis; Tsaris, Aristeidis | Abstract: For the past year, the HEP.TrkX project has been investigating machine learning solutions to LHC particle track reconstruction problems. A variety of models were studied that drew inspiration from computer vision applications and operated on an image-like representation of tracking detector data. While these approaches have shown some promise, image-based methods face challenges in scaling up to realistic HL-LHC data due to high dimensionality and sparsity. In contrast, models that can operate on the spacepoint representation of track measurements ("hits") can exploit the structure of the data to solve tasks efficiently. In this paper we will show two sets of new deep learning models for reconstructing tracks using space-point data arranged as sequences or connected graphs. In the first set of models, Recurrent Neural Networks (RNNs) are used to extrapolate, build, and evaluate track candidates akin to Kalman Filter algorithms. Such models can express their own uncertainty when trained with an appropriate likelihood loss function. The second set of models use Graph Neural Networks (GNNs) for the tasks of hit classification and segment classification. These models read a graph of connected hits and compute features on the nodes and edges. They adaptively learn which hit connections are important and which are spurious. The models are scaleable with simple architecture and relatively few parameters. Results for all models will be presented on ACTS generic detector simulated data.

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI
TL;DR: This article reviews in a selective way the recent research on the interface between machine learning and the physical sciences, including conceptual developments in ML motivated by physical insights, applications of machine learning techniques to several domains in physics, and cross fertilization between the two fields.
Abstract: Machine learning (ML) encompasses a broad range of algorithms and modeling tools used for a vast array of data processing tasks, which has entered most scientific disciplines in recent years. This article reviews in a selective way the recent research on the interface between machine learning and the physical sciences. This includes conceptual developments in ML motivated by physical insights, applications of machine learning techniques to several domains in physics, and cross fertilization between the two fields. After giving a basic notion of machine learning methods and principles, examples are described of how statistical physics is used to understand methods in ML. This review then describes applications of ML methods in particle physics and cosmology, quantum many-body physics, quantum computing, and chemical and material physics. Research and development into novel computing architectures aimed at accelerating ML are also highlighted. Each of the sections describe recent successes as well as domain-specific methodology and challenges.

1,504 citations

Journal ArticleDOI
TL;DR: An overview of Spektral's features is presented and the performance of the methods implemented by the library in scenarios of node classification, graph classification, and graph regression is reported.
Abstract: In this paper we present Spektral, an open-source Python library for building graph neural networks with TensorFlow and the Keras application programming interface. Spektral implements a large set of methods for deep learning on graphs, including message-passing and pooling operators, as well as utilities for processing graphs and loading popular benchmark datasets. The purpose of this library is to provide the essential building blocks for creating graph neural networks, focusing on the guiding principles of user-friendliness and quick prototyping on which Keras is based. Spektral is, therefore, suitable for absolute beginners and expert deep learning practitioners alike. In this work, we present an overview of Spektral's features and report the performance of the methods implemented by the library in scenarios of node classification, graph classification, and graph regression.

133 citations


Cites methods from "Novel deep learning methods for tra..."

  • ...In physics, GNNs have been used to learn physical models of complex systems of interacting particles (Battaglia et al., 2016; Kipf et al., 2018; Sanchez-Gonzalez et al., 2018; Farrell et al., 2018)....

    [...]

Journal ArticleDOI
08 Jan 2021
TL;DR: In this paper, the authors review various applications of graph neural networks in particle physics, including different graph constructions, model architectures and learning objectives, as well as key open problems in particle particle physics for which graph neural network is promising.
Abstract: Particle physics is a branch of science aiming at discovering the fundamental laws of matter and forces. Graph neural networks are trainable functions which operate on graphs---sets of elements and their pairwise relations---and are a central method within the broader field of geometric deep learning. They are very expressive and have demonstrated superior performance to other classical deep learning approaches in a variety of domains. The data in particle physics are often represented by sets and graphs and as such, graph neural networks offer key advantages. Here we review various applications of graph neural networks in particle physics, including different graph constructions, model architectures and learning objectives, as well as key open problems in particle physics for which graph neural networks are promising.

102 citations

Journal ArticleDOI
TL;DR: In this paper, the performance of a jet identification algorithm based on interaction networks (JEDI-net) was investigated to identify all-hadronic decays of high-momentum heavy particles produced at the LHC and distinguish them from ordinary jets originating from the hadronization of quarks and gluons.
Abstract: We investigate the performance of a jet identification algorithm based on interaction networks (JEDI-net) to identify all-hadronic decays of high-momentum heavy particles produced at the LHC and distinguish them from ordinary jets originating from the hadronization of quarks and gluons. The jet dynamics are described as a set of one-to-one interactions between the jet constituents. Based on a representation learned from these interactions, the jet is associated to one of the considered categories. Unlike other architectures, the JEDI-net models achieve their performance without special handling of the sparse input jet representation, extensive pre-processing, particle ordering, or specific assumptions regarding the underlying detector geometry. The presented models give better results with less model parameters, offering interesting prospects for LHC applications.

95 citations

Posted Content
TL;DR: This work demonstrates the applicability of GNNs to these two diverse particle reconstruction problems, which have unique challenges and characteristics, but both have high dimensionality, high degree of sparsity, and complex geometric layouts.
Abstract: Author(s): Ju, Xiangyang; Farrell, Steven; Calafiura, Paolo; Murnane, Daniel; Prabhat; Gray, Lindsey; Klijnsma, Thomas; Pedro, Kevin; Cerati, Giuseppe; Kowalkowski, Jim; Perdue, Gabriel; Spentzouris, Panagiotis; Tran, Nhan; Vlimant, Jean-Roch; Zlokapa, Alexander; Pata, Joosep; Spiropulu, Maria; An, Sitong; Aurisano, Adam; Hewes, Jeremy; Tsaris, Aristeidis; Terao, Kazuhiro; Usher, Tracy | Abstract: Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and measure the kinematic properties of particles produced in high energy collisions and recorded with complex detector systems. Two critical applications are the reconstruction of charged particle trajectories in tracking detectors and the reconstruction of particle showers in calorimeters. These two problems have unique challenges and characteristics, but both have high dimensionality, high degree of sparsity, and complex geometric layouts. Graph Neural Networks (GNNs) are a relatively new class of deep learning architectures which can deal with such data effectively, allowing scientists to incorporate domain knowledge in a graph structure and learn powerful representations leveraging that structure to identify patterns of interest. In this work we demonstrate the applicability of GNNs to these two diverse particle reconstruction problems.

89 citations


Cites background from "Novel deep learning methods for tra..."

  • ...They were first studied for particle tracking applications in [10] and were also studied for the problem of particle and event classification in [3, 13, 15, 7]....

    [...]

  • ...TrkX project to investigate potential new solutions with modern deep learning techniques [11, 10]....

    [...]