Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMachine and Deep Learning Applications in Particle Physics
99
0
0.0
(
0
)
Authors
Dimitri Bourilkov
Ask ChatGPT about the research
No Arabic abstract
The many ways in which machine and deep learning are transforming the analysis and simulation of data in particle physics are reviewed. The main methods based on boosted decision trees and various types of neural networks are introduced, and cutting-edge applications in the experimental and theoretical/phenomenological domains are highlighted. After describing the challenges in the application of these novel analysis techniques, the review concludes by discussing the interactions between physics and machine learning as a two-way street enriching both disciplines and helping to meet the present and future challenges of data-intensive science at the energy and intensity frontiers.
rate research
Read More
New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate 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. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave by Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.
I would like to thank Junk and Lyons (arXiv:2009.06864) for beginning a discussion about replication in high-energy physics (HEP). Junk and Lyons ultimately argue that HEP learned its lessons the hard way through past failures and that other fields could learn from our procedures. They emphasize that experimental collaborations would risk their legacies were they to make a type-1 error in a search for new physics and outline the vigilance taken to avoid one, such as data blinding and a strict $5sigma$ threshold. The discussion, however, ignores an elephant in the room: there are regularly anomalies in searches for new physics that result in substantial scientific activity but dont replicate with more data.
Muons are the most abundant charged particles arriving at sea level originating from the decay of secondary charged pions and kaons. These secondary particles are created when high-energy cosmic rays hit the atmosphere interacting with air nuclei initiating cascades of secondary particles which led to the formation of extensive air showers (EAS). They carry essential information about the extra-terrestrial events and are characterized by large flux and varying angular distribution. To account for open questions and the origin of cosmic rays, one needs to study various components of cosmic rays with energy and arriving direction. Because of the close relation between muon and neutrino production, it is the most important particle to keep track of. We propose a novel tracking algorithm based on the Geometric Deep Learning approach using graphical structure to incorporate domain knowledge to track cosmic ray muons in our 3-D scintillator detector. The detector is modeled using the GEANT4 simulation package and EAS is simulated using CORSIKA (COsmic Ray SImulations for KAscade) with a focus on muons originating from EAS. We shed some light on the performance, robustness towards noise and double hits, limitations, and application of the proposed algorithm in tracking applications with the possibility to generalize to other detectors for astrophysical and collider experiments.
Pions constitute nearly $70%$ of final state particles in ultra high energy collisions. They act as a probe to understand the statistical properties of Quantum Chromodynamics (QCD) matter i.e. Quark Gluon Plasma (QGP) created in such relativistic heavy ion collisions (HIC). Apart from this, direct photons are the most versatile tools to study relativistic HIC. They are produced, by various mechanisms, during the entire space-time history of the strongly interacting system. Direct photons provide measure of jet-quenching when compared with other quark or gluon jets. The $pi^{0}$ decay into two photons make the identification of non-correlated gamma coming from another process cumbersome in the Electromagnetic Calorimeter. We investigate the use of deep learning architecture for reconstruction and identification of single as well as multi particles showers produced in calorimeter by particles created in high energy collisions. We utilize the data of electromagnetic shower at calorimeter cell-level to train the network and show improvements for identification and characterization. These networks are fast and computationally inexpensive for particle shower identification and reconstruction for current and future experiments at particle colliders.
A method for correcting for detector smearing effects using machine learning techniques is presented. Compared to the standard approaches the method can use more than one reconstructed variable to infere the value of the unsmeared quantity on event by event basis. The method is implemented using a sequential neural network with a categorical cross entropy as the loss function. It is tested on a toy example and is shown to satisfy basic closure tests. Possible application of the method for analysis of the data from high energy physics experiments is discussed.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
