- Indico style
- Indico style - inline minutes
- Indico style - numbered
- Indico style - numbered + minutes
- Indico Weeks View
This event follows the productive experience of the first AI4EIC workshop held in 2021 at CFNS and is organized by the EICUG AI WG. The scope of this second workshop is to cover all active and potential areas of applications of AI/ML for the EIC.
The workshop will include sessions on (i) accelerator and detector design (EPIC and potentially detector-2), (ii) connections to theory, (iii) analysis, (iv) reconstruction and particle identification, (v) infrastructure and frontiers in AI/ML and (vi) streaming readout, which will allow discussing different problems, perspectives and leading-edge solutions.
During the workshop we will have AI/ML tutorial sessions provided by experts (academia, national labs, industry). The workshop will also host a Hackathon event (on October 14, whole day event), and a cash prize will be given to the solution winning the competition.
During the first day, we will have talks with perspectives on AI/ML-related research from funding agencies.
AI/ML will be an essential part of all phases of the future EIC and is already contributing to its realization starting from the design and R&D phases. This workshop is a great opportunity to update the community on the progress of ongoing projects and future plans, with discussions on multiple cross-cutting topics that bring together theorists, experimentalists, and AI/ML practitioners.
Live document is here
Instructions on meeting coordinates will be sent via email using the information provided in the registration form.
Location:
William & Mary, Raymond A. Mason School of Business, Alan B. Miller Hall
Room 1019
Break-out rooms (available all time for AI4EIC participants) 1021-1022-1023
Particle accelerator optimization problems deal with non-linear,
multi-objective functions which depend on thousands of time-varying machine components and settings. These properties often meet the limitations of traditional optimization methods and make this problem a perfect candidate for
application of ML-based techniques. In this talk I will present, how ML can improve the control of the beams on the example of the LHC and give a short outlook on the ML application to accelerator design. Main focus of the presentation will be the application of decision tree - based methods to instrumentation faults detection, reconstruction and correction of magnet
errors, and supervised learning for virtual diagnostics, which enables to obtain accurate information of beam properties without time-costly measurements.