A5100633147- Particle physics theoretical and experimental studies
- High-Energy Particle Collisions Research
- Quantum Chromodynamics and Particle Interactions
- Particle Detector Development and Performance
- Computational Physics and Python Applications
- Dark Matter and Cosmic Phenomena
- Cosmology and Gravitation Theories
- Neutrino Physics Research
- Radiation Detection and Scintillator Technologies
- Medical Imaging Techniques and Applications
- Distributed and Parallel Computing Systems
- Advanced Data Storage Technologies
- Parallel Computing and Optimization Techniques
- Scientific Computing and Data Management
- Advanced Neural Network Applications
- Particle Accelerators and Free-Electron Lasers
- CCD and CMOS Imaging Sensors
- Atomic and Subatomic Physics Research
- Astrophysics and Cosmic Phenomena
- Superconducting Materials and Applications
- Neural Networks and Applications
- Anomaly Detection Techniques and Applications
- Advanced Memory and Neural Computing
- Network Packet Processing and Optimization
- Particle accelerators and beam dynamics
Fermi National Accelerator Laboratory
2016-2025
A. Alikhanyan National Laboratory
2022-2024
European Organization for Nuclear Research
2023-2024
Institute of High Energy Physics
2022-2024
Northwestern University
1993-2024
Mayo Clinic in Arizona
2022-2024
University of Antwerp
2023-2024
Vrije Universiteit Brussel
2023-2024
University of Florida
2023
Institute of Social and Preventive Medicine
2022
Recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through improvement of real-time event processing techniques. Machine learning methods are ubiquitous and proven be very powerful in LHC physics, particle as a whole. However, exploration use such techniques low-latency, low-power FPGA hardware has only just begun. FPGA-based trigger data acquisition (DAQ) systems extremely low, sub-microsecond latency requirements that unique physics. We present...
We study the production of a single resonance at LHC and its decay into pair Z bosons. demonstrate how full reconstruction final states allows us to determine spin parity restricts coupling vector gauge Full angular analysis is illustrated with simulation chain including all correlations most general couplings spin-zero, -one, -two resonances Standard Model matter fields. note implications for decaying other states.
We propose a new method for pileup mitigation by implementing "pileup per particle identification" (PUPPI). For each we first define local shape α which probes the collinear versus soft diffuse structure in neighborhood of particle. The former is indicative particles originating from hard scatter and latter interactions. distribution charged pileup, assumed as proxy all used on an event-by-event basis to calculate weight weights describe degree are pileup-like rescale their four-momenta,...
The experimental determination of the properties newly discovered boson at Large Hadron Collider is currently most crucial task in high-energy physics. We show how information about spin, parity, and, more generally, tensor structure couplings can be obtained by studying angular and mass distributions events which resonance decays to pairs gauge bosons, $ZZ$, $WW$, $\ensuremath{\gamma}\ensuremath{\gamma}$. A complete Monte Carlo simulation process...
Jet substructure has emerged to play a central role at the Large Hadron Collider, where it provided numerous innovative ways search for new physics and probe Standard Model, particularly in extreme regions of phase space. In this article we focus on review development use state-of-the-art jet techniques by ATLAS CMS experiments.
In this paper, we study the extent to which CP parity of a Higgs boson, and more generally its anomalous couplings gauge bosons, can be measured at LHC future electron-positron collider. We consider several processes, including boson production in gluon weak fusion association with an electroweak boson. decays $ZZ, WW, \gamma \gamma$, $Z \gamma$. Matrix element approach three decay topologies is developed applied analysis. A complete Monte Carlo simulation above processes proton $e^+e^-$...
We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on FPGAs. By extending the hls4ml library, we demonstrate inference latency of $5\,\mu$s using architectures, targeting microsecond applications like those at CERN Large Hadron Collider. Considering benchmark models trained Street View House Numbers Dataset, various methods model compression in order to fit computational constraints a typical FPGA device used trigger and...
Pattern recognition problems in high energy physics are notably different from traditional machine learning applications computer vision. Reconstruction algorithms identify and measure the kinematic properties of particles produced collisions recorded with complex detector systems. Two critical reconstruction charged particle trajectories tracking detectors showers calorimeters. These two have unique challenges characteristics, but both dimensionality, degree sparsity, geometric layouts....
Abstract This paper presents a roadmap to the application of AI techniques and big data (BD) for different modelling, design, monitoring, manufacturing operation purposes superconducting applications. To help superconductivity researchers, engineers, manufacturers understand viability using BD as future solutions challenges in superconductivity, series short articles are presented outline some potential applications solutions. These futuristic routes their materials/technologies considered...
We present the implementation of binary and ternary neural networks in hls4ml library, designed to automatically convert deep network models digital circuits with FPGA firmware. Starting from benchmark trained floating point precision, we investigate different strategies reduce network's resource consumption by reducing numerical precision parameters or ternary. discuss trade-off between model accuracy consumption. In addition, show how balance latency retaining full on a selected subset...
Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged tracking, jet tagging, and clustering. An important domain the application of these is FGPA-based first layer real-time data filtering at CERN Large Hadron Collider, which has strict latency resource constraints. We discuss how design distance-weighted graph that can be executed with a less than 1$\mu\mathrm{s}$ on an FPGA. To do so, we consider representative...
Despite advances in the programmable logic capabilities of modern trigger systems, a significant bottleneck remains amount data to be transported from detector off-detector where decisions are made. We demonstrate that neural network autoencoder model can implemented radiation tolerant ASIC perform lossy compression alleviating transmission problem while preserving critical information energy profile. For our application, we consider high-granularity calorimeter CMS experiment at CERN Large...
We describe a method for precisely regulating the gradient magnet power supply at Fermilab Booster accelerator complex using neural network trained via reinforcement learning. demonstrate preliminary results by training surrogate machine-learning model on real data to emulate environment, and this in turn train its regulation task. additionally show how networks be deployed control purposes may compiled execute field-programmable gate arrays. This capability is important operational...
Rapidly increasing urbanisation along with ageing populations, climate change, environmental degradation, COVID-19, and other pandemics present substantial challenges for people living in cities communities. The capacity to identify respond urban related health, equity, sustainability varies greatly across national subnational governments around the globe, because of available human financial resources, structures governance participation, existing policy frameworks, which are all important...
Particle physics today faces the challenge of explaining mystery dark matter, origin matter over anti-matter in Universe, neutrino masses, apparent fine-tuning electro-weak scale, and many other aspects fundamental physics. Perhaps most striking frontier to emerge search for answers involves new at mass scales comparable familiar below GeV-scale, or even radically below, down sub-eV scales, with very feeble interaction strength. New theoretical ideas address questions predict such feebly...
We develop a pipeline to streamline neural architecture codesign for physics applications reduce the need ML expertise when designing models novel tasks. Our method employs search and network compression in two-stage approach discover hardware efficient models. This consists of global stage that explores wide range architectures while considering constraints, followed by local fine-tunes compresses most promising candidates. exceed performance on various tasks show further speedup through...
As machine learning (ML) increasingly serves as a tool for addressing real-time challenges in scientific applications, the development of advanced tooling has significantly reduced time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such model synthesis, are now becoming limiting factors rapid iteration To reduce these emerging constraints,...
<title>Abstract</title> Precise cell classification is essential in biomedical diagnostics and therapeutic monitoring, particularly for identifying diverse types involved various diseases. Traditional methods such as flow cytometry depend on molecular labeling which often costly, time-intensive, can alter integrity. To overcome these limitations, we present a label-free machine learning framework classification, designed real-time sorting applications using bright-field microscopy images....