AI for Experiments - Research Collaboration (JTFI Workshop, Part II) Virtual

US/Central
Virtual

Virtual

Eric Jonas (U of Chicago), Jayakar (Charles) Thangaraj (Fermilab), Mauricio Suarez (Fermilab), Nhan Tran (Fermilab), Paul Fenter (Argonne), Yuxin Chen (U of Chicago)
Description

Registration is Now Open for Virtual Participants!

AI for Experiments - Research Collaborations (JTFI Workshop-Part II)

The AI for Experiments – Research Collaborations workshop will have an in-person part and a virtual part this year as a balance to satisfy health requirements and allow for broad participation. The event will be held on Thursday, October 20th, 2022.

The workshop hosted by Fermi National Accelerator Laboratory, the University of Chicago, and Argonne National Laboratory will focus on opportunities to collaborate on AI research between the three institutions. We expect participants from the three institutions who are interested in collaborating and pushing the frontier in AI crucial areas such as inverse problems, uncertainty, active learning, and reinforcement learning in the context of measurements.

This event concludes the “AI + measurements” JTFI workshop, which aims to forge new connections and collaborations between the organizing institutions. The first part of this two-part workshop is here

What should you do? The organizing committee invites you to register for the workshop before noon October 6, 2022. Registered participants will be able to virtually attend the morning keynote talks by the host institutions. Also, a special interactive virtual session in the evening will be made available for registered participants for questions, brainstorming collaboration opportunities, and discussions around the workshop topics (see agenda).

Deadline to register: October 6th at 5:30 PM CDT.

Connection information will be e-mailed to registrants 24 hours prior to the event.

Who should attend? “AI for experiments – research collaborations” will provide an opportunity to discuss interdisciplinary areas in AI for experiments in sciences and engineering. Targeted attendees are researchers working at the frontlines of AI or experimentalists with AI-relevant problems; researchers, post-docs, and graduate students are welcome to attend. 

Objective: to forge new connections between Fermilab, University of Chicago, Toyota Technological Institute at Chicago (TTIC), and Argonne on the topics of intersection of AI and experimental measurements. Researchers from diverse domains such as data acquisition, metrology, cosmology, astronomy, particle physics, accelerator science and chemistry are encouraged to participate and gain exposure to cutting-edge AI research and tools.

Sponsors: This workshop is sponsored by the University of Chicago’s Office of Research and National Laboratories Joint Task Force Initiative’s “AI+Science” grant and the Center for Data and Computing (CDAC) - an intellectual hub and incubator for data science and artificial intelligence research at the University of Chicago.

 

 

Participants
  • Aakaash Narayanan
  • Arun Bommannavar
  • Becky Nevin
  • Benedetto Di Ruzza
  • Chandrachur Bhattacharya
  • Eliu Huerta
  • Eric Dufresne
  • Eric Jonas
  • Guosheng Ye
  • J. Charles Thangaraj
  • Jie Xu
  • jim huang
  • Kamlesh Suthar
  • Kent Bostick
  • Kevin Klepper
  • Mauricio Suarez
  • Max Wyman
  • Meltem Urgun-Demirtas
  • Michael Prince
  • Nhan Tran
  • Nina Andrejevic
  • Paul Fenter
  • shaohong Gu
  • Smita Darmora
  • Srutarshi Banerjee
  • Tammy Gloss
  • Tirupathi Malavath
  • Tyler Eastmond
  • Wilkie Olin-Ammentorp
  • Xingfu Wu
  • Yuxin Chen
Event Organizer: Mauricio Suarez
    • 08:55 09:00
      Welcome
      Conveners: Bonnie Fleming (Fermilab), Mauricio Suarez (Fermilab)
    • 09:00 09:30
      Presentation: How Can ML Advance Scientific Measurement?
      Convener: Eric Jonas (U of Chicago)
    • 09:30 10:00
      Presentation: HPI + AI-Enabled X-ray Science at the Advanced Photon Source
      Convener: Mathew Cherukara (Argonne)
    • 10:00 10:15
      Break 15m
    • 10:15 10:45
      Presentation: Efficient Machine Learning in HEP
      Convener: Jennifer Ngadiuba (FNAL)
    • 10:45 11:15
      Presentation: Quantifying Predictive Uncertainty with Conformal Inference
      Convener: Rina Barber (University of Chicago)
    • 11:15 15:00
      Break 3h 45m
    • 15:00 15:50
      Panel: Questions & Panel Discussion
      Conveners: Eric Jonas (U of Chicago), Nhan Tran (FNAL), Paul Fenter (Argonne), Yuxin Chen (University of Chicago)
    • 15:50 16:00
      Closing
      Convener: James Amundson (Fermilab)