Difference between revisions of "AIOP Aug. 5, 2024"

From epsciwiki
Jump to navigation Jump to search
Line 76: Line 76:
 
=== 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 -->
 +
<h1>B-5-24 AIOP Target</h1>
 +
 +
<p><strong>Attendees:</strong> David, Thomas, Patrick, Armen, James</p>
 +
 +
<ul>
 +
  <li><strong>Announcements</strong>
 +
    <ul>
 +
      <li>David regails with Icelandic tales</li>
 +
    </ul>
 +
  </li>
 +
 
 +
  <li><strong>Conferences</strong>
 +
    <ul>
 +
      <li>CAARI-SNEAP went well. Malachi found it interesting</li>
 +
      <li>Torri scored a contact who is reproducing Hydra (but is farther behind)</li>
 +
      <li>PSTDP deadline extension</li>
 +
    </ul>
 +
  </li>
 +
 
 +
  <li><strong>Progress</strong>
 +
    <ul>
 +
      <li>Armen presents some slides
 +
        <ul>
 +
          <li>Model overestimating uncertainty</li>
 +
          <li>Proposed things that we could do to fix/make the model better:
 +
            <ul>
 +
              <li>HPO</li>
 +
              <li>Kernel selection</li>
 +
              <li>Feature engineering</li>
 +
              <li>Input normalization</li>
 +
              <li>Etc etc</li>
 +
            </ul>
 +
          </li>
 +
          <li>Discussion of graphs
 +
            <ul>
 +
              <li>Showing overestimate</li>
 +
            </ul>
 +
          </li>
 +
          <li>Malachi thinks we need to go to a different model for UQ
 +
            <ul>
 +
              <li>Regression with conditional</li>
 +
              <li>MC dropout</li>
 +
              <li>Will show where in the toolkit these features are/the code to do it</li>
 +
            </ul>
 +
          </li>
 +
        </ul>
 +
      </li>
 +
    </ul>
 +
  </li>
 +
 +
  <li><strong>Milestones</strong>
 +
    <ul>
 +
      <li>David removed some that were rescheduled from the FWP doc post lower funding</li>
 +
      <li>David asked about NMR waveform time evolution
 +
        <ul>
 +
          <li>Maxwell discussed fluctuations in temperature due to beam on/wobble</li>
 +
          <li>May be better Ts to look at to get more info</li>
 +
        </ul>
 +
      </li>
 +
    </ul>
 +
  </li>
 +
</ul>
  
  
 
==== Action Items ====
 
==== Action Items ====

Revision as of 16:48, 19 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 sent to DOE July 17th
    • David back from Iceland DavidAndMomIceland2024.pngHarrietIceland2024.png
  3. Conferences/Workshops
  4. Project Progress
  5. PIER Activities
    • Middle School Data Science Hackathon Workshop
    • HUGS mini-Workshop - COMPLETED!
  6. AOT



Minutes

B-5-24 AIOP Target

Attendees: David, Thomas, Patrick, Armen, James

  • Announcements
    • David regails with Icelandic tales
  • Conferences
    • CAARI-SNEAP went well. Malachi found it interesting
    • Torri scored a contact who is reproducing Hydra (but is farther behind)
    • PSTDP deadline extension
  • Progress
    • Armen presents some slides
      • Model overestimating uncertainty
      • Proposed things that we could do to fix/make the model better:
        • HPO
        • Kernel selection
        • Feature engineering
        • Input normalization
        • Etc etc
      • Discussion of graphs
        • Showing overestimate
      • Malachi thinks we need to go to a different model for UQ
        • Regression with conditional
        • MC dropout
        • Will show where in the toolkit these features are/the code to do it
  • Milestones
    • David removed some that were rescheduled from the FWP doc post lower funding
    • David asked about NMR waveform time evolution
      • Maxwell discussed fluctuations in temperature due to beam on/wobble
      • May be better Ts to look at to get more info


Action Items