Difference between revisions of "AIOP Jul. 8, 2024"

From epsciwiki
Jump to navigation Jump to search
 
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, Patrick Moran, Malachi -->
 +
<ul>
 +
  <li>AIOP target
 +
    <ul>
 +
      <li>Torri, Thomas, David, Armen, James, Patrick, Malachi</li>
 +
    </ul>
 +
  </li>
 +
  <li>Announcements
 +
    <ul>
 +
      <li>Quarterly report due the 26th of July</li>
 +
      <li>Cancelling July 22nd due to correlated ooo</li>
 +
    </ul>
 +
  </li>
 +
  <li>Project Progress
 +
    <ul>
 +
      <li>Data mining
 +
        <ul>
 +
          <li>Torri
 +
            <ul>
 +
              <li>Switched baseline fit function to x-x0 and showed Pearson R correlation values
 +
                <ul>
 +
                  <li>Not seeing much for proton but seeing some stuff for deuteron</li>
 +
                  <li>Thomas questioned the different NaNs; James explained that it was due to certain values not being recorded at different times</li>
 +
                  <li>Need to change this fit function to remove the b term which could crystallize some correlations
 +
                    <ul>
 +
                      <li>Done and will rerun</li>
 +
                    </ul>
 +
                  </li>
 +
                </ul>
 +
              </li>
 +
            </ul>
 +
          </li>
 +
          <li>Armen
 +
            <ul>
 +
              <li>Reviewed fitting process and gave it more data and it can learn (pos and neg together)
 +
                <ul>
 +
                  <li>Malachi requests uncertainty bands
 +
                    <ul>
 +
                      <li>Armen has preliminary he is withholding while he works to understand the toolkit</li>
 +
                    </ul>
 +
                  </li>
 +
                </ul>
 +
              </li>
 +
            </ul>
 +
          </li>
 +
          <li>Torri gave cleaned proton data
 +
            <ul>
 +
              <li>Training the model right now…will take a while</li>
 +
              <li>Questions on TGT:PT12:Separator_F. High number of NaNs
 +
                <ul>
 +
                  <li>James: not as valuable as refrigerator flow</li>
 +
                </ul>
 +
              </li>
 +
              <li>Also trained by replacing cc with area</li>
 +
              <li>Torri suggested checking label on outliers as they might not be "good" runs</li>
 +
              <li>Next step: take surrogate (assuming it is satisfactory) and put in gym for the RL step</li>
 +
            </ul>
 +
          </li>
 +
        </ul>
 +
      </li>
 +
      <li>Reviewed Milestones
 +
        <ul>
 +
          <li>M01
 +
            <ul>
 +
              <li>SANE data is quite different so setting it aside for now (Armen doesn’t need)</li>
 +
            </ul>
 +
          </li>
 +
          <li>M02</li>
 +
          <li>M03
 +
            <ul>
 +
              <li>Done</li>
 +
            </ul>
 +
          </li>
 +
          <li>M04
 +
            <ul>
 +
              <li>James has a tool</li>
 +
            </ul>
 +
          </li>
 +
        </ul>
 +
      </li>
 +
    </ul>
 +
  </li>
 +
</ul>
  
  
 
==== Action Items ====
 
==== Action Items ====

Latest revision as of 17:09, 5 August 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:

  1. Previous Meeting
  2. Announcements
    • Quarterly report due to DOE July 26th
    • David OoO Jul. 20 - Aug. 5 (Jul. 22 meeting: Thomas chair, Torri review slides)
  3. Conferences/Workshops
    • CAARI-SNEAP (July 21-26) Torri
    • PSTDP2024 (Sept. 22-27) Patrick will submit abstract, Jiawei will attend
  4. Project Progress
  5. PIER Activities
    • Middle School Data Science Hackathon Workshop
    • HUGS mini-Workshop - COMPLETED!
  6. AOT


Minutes

  • AIOP target
    • Torri, Thomas, David, Armen, James, Patrick, Malachi
  • Announcements
    • Quarterly report due the 26th of July
    • Cancelling July 22nd due to correlated ooo
  • Project Progress
    • Data mining
      • Torri
        • Switched baseline fit function to x-x0 and showed Pearson R correlation values
          • Not seeing much for proton but seeing some stuff for deuteron
          • Thomas questioned the different NaNs; James explained that it was due to certain values not being recorded at different times
          • Need to change this fit function to remove the b term which could crystallize some correlations
            • Done and will rerun
      • Armen
        • Reviewed fitting process and gave it more data and it can learn (pos and neg together)
          • Malachi requests uncertainty bands
            • Armen has preliminary he is withholding while he works to understand the toolkit
      • Torri gave cleaned proton data
        • Training the model right now…will take a while
        • Questions on TGT:PT12:Separator_F. High number of NaNs
          • James: not as valuable as refrigerator flow
        • Also trained by replacing cc with area
        • Torri suggested checking label on outliers as they might not be "good" runs
        • Next step: take surrogate (assuming it is satisfactory) and put in gym for the RL step
    • Reviewed Milestones
      • M01
        • SANE data is quite different so setting it aside for now (Armen doesn’t need)
      • M02
      • M03
        • Done
      • M04
        • James has a tool


Action Items

Retrieved from "https://wiki.jlab.org/epsciwiki/index.php?title=AIOP_Jul._8,_2024&oldid=5285"