1.
|
Applications and Techniques for Fast Machine Learning in Science
/ Deiana, Allison McCarn (Southern Methodist U.) ; Tran, Nhan (Fermilab ; Northwestern U. (main)) ; Agar, Joshua (Lehigh U. (main)) ; Blott, Michaela (Xilinx, Dublin) ; Di Guglielmo, Giuseppe (Columbia U. (main)) ; Duarte, Javier (UC, San Diego) ; Harris, Philip (MIT) ; Hauck, Scott (George Washington U. (main)) ; Liu, Mia (Purdue U.) ; Neubauer, Mark S. (Illinois U., Urbana) et al.
In this community review report, we discuss applications and techniques for fast machine learning (ML) in science -- the concept of integrating power ML methods into the real-time experimental data processing loop to accelerate scientific discovery. The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML across a number of scientific domains; techniques for training and implementing performant and resource-efficient ML algorithms; and computing architectures, platforms, and technologies for deploying these algorithms. [...]
arXiv:2110.13041; FERMILAB-PUB-21-502-AD-E-SCD.-
2022-04-12 - 56 p.
- Published in : Front. Big Data 5 (2022) 787421
Fulltext: 2110.13041 - PDF; fermilab-pub-21-502-ad-e-scd - PDF; Fulltext from Publisher: PDF; External link: Fermilab Library Server
|
|
2.
|
|
Experience with Rucio in the wider HEP community
/ Barisits, Martin (CERN) ; Beermann, Thomas (Wuppertal U.) ; Cameron, David (Oslo U.) ; Clark, James Alexander (Caltech ; Georgia Tech) ; Di Maria, Riccardo (CERN) ; Fronzé, Gabriele Gaetano (INFN, Turin) ; Johnson, Ian (Rutherford) ; Lassnig, Mario (CERN) ; Serfon, Cédric (Brookhaven) ; Vaandering, Eric W (Fermilab)
Managing the data of scientific projects is an increasingly complicated challenge, which was usually met by developing experiment-specific solutions. [...]
ATL-SOFT-PROC-2021-009 ; FERMILAB-CONF-21-753-SCD.
-
2021. - 11 p.
Original Communication (restricted to ATLAS) - Full text
|
|
3.
|
|
4.
|
Large-scale HPC deployment of Scalable CyberInfrastructure for Artificial Intelligence and Likelihood Free Inference (SCAILFIN)
/ Hildreth, Michael (Notre Dame U.) ; Hurtado Anampa, Kenyi Paolo (Notre Dame U.) ; Kankel, Cody (Notre Dame U.) ; Hampton, Scott (Notre Dame U.) ; Brenner, Paul (Notre Dame U.) ; Johnson, Irena (Notre Dame U.) ; Simko, Tibor (CERN)
The NSF-funded Scalable CyberInfrastructure for Artificial Intelligence and Likelihood Free Inference (SCAILFIN) project aims to develop and deploy artificial intelligence (AI) and likelihood-free inference (LFI) techniques and software using scalable cyberinfrastructure (CI) built on top of existing CI elements. Specifically, the project has extended the CERN-based REANA framework, a cloud-based data analysis platform deployed on top of Kubernetes clusters that was originally designed to enable analysis reusability and reproducibility. [...]
2020 - 6 p.
- Published in : EPJ Web Conf. 245 (2020) 09011
Fulltext by publisher: PDF;
In : 24th International Conference on Computing in High Energy and Nuclear Physics, Adelaide, Australia, 4 - 8 Nov 2019, pp.09011
|
|
5.
|
Abstracting container technologies and transfer mechanisms in the Scalable CyberInfrastructure for Artificial Intelligence and Likelihood Free Inference (SCAILFIN) project
/ Hurtado Anampa, Kenyi (Notre Dame U.) ; Kankel, Cody (Notre Dame U.) ; Hildreth, Mike (Notre Dame U.) ; Brenner, Paul (Notre Dame U.) ; Johnson, Irena (Notre Dame U.) ; Hampton, Scott (Notre Dame U.) ; Simko, Tibor (CERN)
High Performance Computing (HPC) facilities provide vast computational power and storage, but generally work on fixed environments designed to address the most common software needs locally, making it challenging for users to bring their own software. To overcome this issue, most HPC facilities have added support for HPC friendly container technologies such as Shifter, Singularity, or Charliecloud. [...]
2020 - 6 p.
- Published in : EPJ Web Conf. 245 (2020) 07023
Fulltext: PDF;
In : 24th International Conference on Computing in High Energy and Nuclear Physics, Adelaide, Australia, 4 - 8 Nov 2019, pp.07023
|
|
6.
|
Support for HTCondor high-throughput computing workflows in the REANA reusable analysis platform
/ Maciulaitis, Rokas (Ministere des affaires etrangeres et europeennes (FR)) ; Brener, Paul (University of Notre Dame (US)) ; Hampton, Scott (University of Notre Dame (US)) ; Hildreth, Mike (University of Notre Dame (US)) ; Hurtado Anampa, Kenyi Paolo (University of Notre Dame (US)) ; Johnson, Irena (University of Notre Dame (US)) ; Kankel, Cody (University of Notre Dame (US)) ; Okraska, Jan (University of Warsaw (PL)) ; Rodriguez Rodriguez, Diego (CERN) ; Simko, Tibor (CERN)
REANA is a reusable and reproducible data analysis platform allowing researchers to structure their analysis pipelines and run them on remote containerised compute clouds. REANA supports several different workflows systems (CWL, Serial, Yadage) and uses Kubernetes’ job execution backend. [...]
CERN-IT-2019-004.-
Geneva : CERN, 2019 - 2 p.
Fulltext: PDF;
In : 15th eScience IEEE International Conference, San Diego, United States, 24 - 27 Sep 2019, pp.eScience
|
|
7.
|
Support for HTCondor High-Throughput Computing Workflows in the REANA Reusable Analysis Platform
|
8.
|
Construction and tests of demonstrator modules for a 3-D axial PET system for brain or small animal imaging
/ Chesi, E (Ohio State U.) ; Nappi, E (INFN, Bari) ; Clinthorne, N (Michigan U.) ; Pauss, P (Zurich, ETH) ; Meddi, F (Rome U.) ; Beltrame, P (CERN) ; Kagan, H (Ohio State U.) ; Braem, A (CERN) ; Casella, C (Zurich, ETH) ; Djambazov, G (Zurich, ETH) et al.
The design and construction of a PET camera module with high sensitivity, full 3-D spatial reconstruction and very good energy resolution is presented. The basic principle consists of an axial arrangement of long scintillation crystals around the Field Of View (FOV), providing a measurement of the transverse coordinates of the interacting 511 keV gamma ray. [...]
2011
- Published in : Nucl. Instrum. Methods Phys. Res., A 636 (2011) S226-S230
In : 7th International Symposium on the Development and Application of Semiconductor Tracking Detectors, Hiroshima, Japan, 29 Aug - 01 Sep 2009, pp.S226-S230
|
|
9.
|
|
10.
|
The AX-PET project : Demonstration of a high resolution axial 3D PET
/ Bolle, E (Oslo U.) ; Braem, A (CERN) ; Casella, C (Zurich, ETH) ; Chesi, E (Ohio State U.) ; Clinthorne, N (Michigan U.) ; Cochran, E (Ohio State U.) ; De Leo, R (INFN, Bari) ; Dissertori, G (Zurich, ETH) ; Djambazov, G (Zurich, ETH) ; Fanti, V (CERN) et al.
The AX-PET is a new geometrical concept for a high resolution 3D PET scanner, based on matrices of axially oriented LYSO crystals interleaved by stacks of WLS, both individually read out by G-APDs. A PET demonstrator, based on two detector modules used in coincidence, is currently under construction..
2010
- Published in : Nucl. Instrum. Methods Phys. Res., A 623 (2010) 214-216
In : 11th Pisa Meeting on Advanced Detectors on Frontier Detectors For Frontier Physics, La Biodola, Italy, 24 - 30 May 2009, pp.214-216
|
|