Author: Edelen, A.L.
Paper Title Page
MOPA55 Facilitating Machine Learning Collaborations Between Labs, Universities, and Industry 164
 
  • J.P. Edelen, D.T. Abell, D.L. Bruhwiler, S.J. Coleman, N.M. Cook, A. Diaw, J.A. Einstein-Curtis, C.C. Hall, M.C. Kilpatrick, B. Nash, I.V. Pogorelov
    RadiaSoft LLC, Boulder, Colorado, USA
  • K.A. Brown
    BNL, Upton, New York, USA
  • S. Calder
    ORNL RAD, Oak Ridge, Tennessee, USA
  • A.L. Edelen, B.D. O’Shea, R.J. Roussel
    SLAC, Menlo Park, California, USA
  • C.M. Hoffmann
    ORNL, Oak Ridge, Tennessee, USA
  • E.-C. Huang
    LANL, Los Alamos, New Mexico, USA
  • P. Piot
    Northern Illinois University, DeKalb, Illinois, USA
  • C. Tennant
    JLab, Newport News, Virginia, USA
 
  It is clear from nu­mer­ous re­cent com­mu­nity re­ports, pa­pers, and pro­pos­als that ma­chine learn­ing is of tremen­dous in­ter­est for par­ti­cle ac­cel­er­a­tor ap­pli­ca­tions. The quickly evolv­ing land­scape con­tin­ues to grow in both the breadth and depth of ap­pli­ca­tions in­clud­ing physics mod­el­ing, anom­aly de­tec­tion, con­trols, di­ag­nos­tics, and analy­sis. Con­se­quently, lab­o­ra­to­ries, uni­ver­si­ties, and com­pa­nies across the globe have es­tab­lished ded­i­cated ma­chine learn­ing (ML) and data-sci­ence ef­forts aim­ing to make use of these new state-of-the-art tools. The cur­rent fund­ing en­vi­ron­ment in the U.S. is struc­tured in a way that sup­ports spe­cific ap­pli­ca­tion spaces rather than larger col­lab­o­ra­tion on com­mu­nity soft­ware. Here, we dis­cuss the ex­ist­ing col­lab­o­ra­tion bot­tle­necks and how a shift in the fund­ing en­vi­ron­ment, and how we de­velop col­lab­o­ra­tive tools, can help fuel the next wave of ML ad­vance­ments for par­ti­cle ac­cel­er­a­tors.  
DOI • reference for this paper ※ doi:10.18429/JACoW-NAPAC2022-MOPA55  
About • Received ※ 10 August 2022 — Revised ※ 11 August 2022 — Accepted ※ 22 August 2022 — Issue date ※ 01 September 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUXE1
The Importance of Data, High-Performance Computing, and Artificial Intelligence/Machine Learning  
 
  • C.M. Sweeney
    LANL, Los Alamos, New Mexico, USA
  • A.L. Edelen
    SLAC, Menlo Park, California, USA
  • D.E. Martin
    ANL, Lemont, Illinois, USA
 
  As ex­ist­ing ac­cel­er­a­tor fa­cil­i­ties are up­graded and new fa­cil­i­ties come on­line, data vol­umes and ve­loc­ity are in­creas­ing even with shorter data col­lec­tion times. High-per­for­mance com­put­ing (HPC) sys­tems doing sim­u­la­tion, data an­a­lyt­ics and ar­ti­fi­cial in­tel­li­gence/ma­chine learn­ing (AI/ML) are play­ing a major role in pre-ex­per­i­ment plan­ning, de­sign of ex­per­i­ments, real-time beam line and ex­per­i­ment analy­sis and con­trol, and post-run data pro­cess­ing. Sim­u­la­tion and AI in­cor­po­rated into ex­per­i­men­tal data analy­sis work­flows are mak­ing ef­fi­cient use of ex­pen­sive fa­cil­i­ties and ac­cel­er­at­ing sci­en­tific dis­cov­er­ies. HPC is ex­pe­ri­enc­ing its own growth, with ex­as­cale com­put­ers and AI ac­cel­er­a­tion com­ing on­line at sev­eral su­per­com­puter cen­ters. AI/ML is in the midst of rapid growth of tech­niques and ex­pan­sion into new ap­pli­ca­tion areas. This ses­sion will focus on cur­rent and emerg­ing tech­nolo­gies in HPC, ex­per­i­men­tal work­flows, and AI/ML tech­niques to help you in­cor­po­rate them into your own re­search. Dr. D. Mar­tin will pro­vide "HPC Overview" fol­lowed by "Work­flows" by Dr. C. Sweeney. "AI and ML" by Dr. A. Ede­len will be fol­lowed by com­mu­nity dis­cus­sions and ques­tions from the au­di­ence.  
slides icon Slides TUXE1 [11.946 MB]  
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUXE3
Artificial Intelligence and Machine Learning for Particle Accelerators  
 
  • A.L. Edelen
    SLAC, Menlo Park, California, USA
 
  As ex­ist­ing ac­cel­er­a­tor fa­cil­i­ties are up­graded and new fa­cil­i­ties come on­line, data vol­umes and ve­loc­ity are in­creas­ing even with shorter data col­lec­tion times. High-per­for­mance com­put­ing (HPC) sys­tems doing sim­u­la­tion, data an­a­lyt­ics and ar­ti­fi­cial in­tel­li­gence/ma­chine learn­ing (AI/ML) are play­ing a major role in pre-ex­per­i­ment plan­ning, de­sign of ex­per­i­ments, real-time beam line and ex­per­i­ment analy­sis and con­trol, and post-run data pro­cess­ing. Sim­u­la­tion and AI in­cor­po­rated into ex­per­i­men­tal data analy­sis work­flows are mak­ing ef­fi­cient use of ex­pen­sive fa­cil­i­ties and ac­cel­er­at­ing sci­en­tific dis­cov­er­ies. HPC is ex­pe­ri­enc­ing its own growth, with ex­as­cale com­put­ers and AI ac­cel­er­a­tion com­ing on­line at sev­eral su­per­com­puter cen­ters. AI/ML is in the midst of rapid growth of tech­niques and ex­pan­sion into new ap­pli­ca­tion areas. This ses­sion will focus on cur­rent and emerg­ing tech­nolo­gies in HPC, ex­per­i­men­tal work­flows, and AI/ML tech­niques to help you in­cor­po­rate them into your own re­search. Dr. D. Mar­tin will pro­vide "HPC Overview" fol­lowed by "Work­flows" by Dr. C. Sweeney. "AI and ML" by Dr. A. Ede­len will be fol­lowed by com­mu­nity dis­cus­sions and ques­tions from the au­di­ence.  
slides icon Slides TUXE3 [17.252 MB]  
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)