Difference between revisions of "AIOP Sep. 30, 2024"
Line 73: | Line 73: | ||
=== Minutes === | === Minutes === | ||
<!-- Attendees: Torri Jeske, Thomas Britton, David Lawrence, Armen Kasparian, Naomi Jarvis, Patrick Moran, Chris Keith, James Maxwell --> | <!-- Attendees: Torri Jeske, Thomas Britton, David Lawrence, Armen Kasparian, Naomi Jarvis, Patrick Moran, Chris Keith, James Maxwell --> | ||
+ | <ul> | ||
+ | <li><strong>AIOP target 9-30</strong></li> | ||
+ | <li><strong>Attendees:</strong> Thomas, Malachi, Patrick, Armen, David, Torri</li> | ||
+ | |||
+ | <li><strong>Talks</strong> | ||
+ | <ul> | ||
+ | <li>Patrick should post his slides</li> | ||
+ | <li>Torri is half done with the AIOP CHEP talk</li> | ||
+ | </ul> | ||
+ | </li> | ||
+ | |||
+ | <li><strong>Progress</strong> | ||
+ | <ul> | ||
+ | <li><strong>Torri</strong> | ||
+ | <ul> | ||
+ | <li>Reviewed lack of and odd correlation plots</li> | ||
+ | <li>Split by Anneal (dosing)</li> | ||
+ | <ul> | ||
+ | <li>Showed a dose vs index plot</li> | ||
+ | <li>Irregular number of indices in each data file</li> | ||
+ | <li>Same baseline for many runs</li> | ||
+ | <li>Showed own fits with a third order (background)</li> | ||
+ | <li>Nothing jumping out</li> | ||
+ | <li>Suggested looking at baseline sub</li> | ||
+ | </ul> | ||
+ | </ul> | ||
+ | </li> | ||
+ | |||
+ | <li><strong>Armen</strong> | ||
+ | <ul> | ||
+ | <li>A trip down memory lane</li> | ||
+ | <li>No version control</li> | ||
+ | <li>Copy paste galore!</li> | ||
+ | <li>Moved from scikit/jupyter to JLab core and BoTorch</li> | ||
+ | <li>Showed a really good model that fits true values well</li> | ||
+ | <ul> | ||
+ | <li>Found a bug in model loading preventing newer models from being used</li> | ||
+ | </ul> | ||
+ | <li>Continuing migration to JLab Core</li> | ||
+ | <li>Can look at outliers</li> | ||
+ | <li>David + Thomas want to see prediction vs true by time</li> | ||
+ | </ul> | ||
+ | </li> | ||
+ | </ul> | ||
+ | </li> | ||
+ | </ul> | ||
==== Action Items ==== | ==== Action Items ==== |
Revision as of 18:01, 30 September 2024
The current weekly meeting time is every other Monday at 13:00 US/Eastern
Connection Info:
You can connect using ZOOM Video conferencing (ID: 160 515 9491). (Click "Expand" to the right for details -->):
One tap mobile: US: +16692545252,,1602484178# or +16468287666,,1602484178#
Meeting URL: https://jlab-org.zoomgov.com/j/1605159491?pwd=ZnB0Vkp0SCtYZmRPWG1hRGVnQVprUT09&from=addon
Meeting ID: 160 515 9491
Passcode: 680042
Join by Telephone
For higher quality, dial a number based on your current location.
Dial: +1 669 254 5252 US (San Jose)
+1 646 828 7666 US (New York)
+1 646 964 1167 US (US Spanish Line)
+1 551 285 1373 US (New Jersey)
+1 669 216 1590 US (San Jose)
+1 415 449 4000 US (US Spanish Line)
833 568 8864 US Toll-free
Meeting ID: 160 515 9491
International numbers
Join from an H.323/SIP room system
H.323: 161.199.138.10 (US West)
161.199.136.10 (US East)
Meeting ID: 160 515 9491
Passcode: 680042
SIP: 1605159491@sip.zoomgov.com
Passcode: 680042
One tap mobile: US: +16692545252,,1601987443# or +16468287666,,1601987443#
Meeting URL: https://jlab-org.zoomgov.com/j/1605159491?pwd=ZnB0Vkp0SCtYZmRPWG1hRGVnQVprUT09&from=addon
Meeting ID: 160 515 9491
Passcode: 680042
AIOP - Polarized Target
Agenda:
- Previous Meeting
- Announcements
- Conferences/Workshops
- PSTDP2024 (Sept. 22-27) (Patrick speaks 9/26 @ 10am)
- CHEP2024 (Oct. 19-25, Krakow, Poland)Oral presentation accepted (Torri)
- ICFA Beam Dynamics Mini-Workshop on Machine Learning for Particle Accelerators (Apr. 8-11 CERN)
- Project Progress
- Data mining/preparation
- GitHub AIOP Project (AIOP-Target issues)
- Milestones: PDF(GitHub AIOP Project AIOP-Target issues FTE Profiles)
- PIER Activities
- Middle School Data Science Hackathon Workshop (Oct. 16)
HUGS mini-Workshop- COMPLETED!
- AOT
Minutes
- AIOP target 9-30
- Attendees: Thomas, Malachi, Patrick, Armen, David, Torri
- Talks
- Patrick should post his slides
- Torri is half done with the AIOP CHEP talk
- Progress
- Torri
- Reviewed lack of and odd correlation plots
- Split by Anneal (dosing)
- Showed a dose vs index plot
- Irregular number of indices in each data file
- Same baseline for many runs
- Showed own fits with a third order (background)
- Nothing jumping out
- Suggested looking at baseline sub
- Armen
- A trip down memory lane
- No version control
- Copy paste galore!
- Moved from scikit/jupyter to JLab core and BoTorch
- Showed a really good model that fits true values well
- Found a bug in model loading preventing newer models from being used
- Continuing migration to JLab Core
- Can look at outliers
- David + Thomas want to see prediction vs true by time
- Torri