Difference between revisions of "AIOP May 13, 2024"

From epsciwiki
Jump to navigation Jump to search
(Created page with "The current weekly meeting time is every other Monday at 13:00 US/Eastern === Connection Info: === <div class="toccolours mw-collapsible mw-collapsed"> You can connect using...")
 
 
Line 66: Line 66:
  
 
=== Minutes ===
 
=== Minutes ===
<!-- Attendees: Malachi S., Torri J., Thomas B., Jiawei G., David L., Patrick M., Armen K., James M., Naomi J., Chris K. -->
+
<!-- Attendees: Torri J., Thomas B., David L., Patrick M., Armen K. -->
 +
<ul>
 +
    <li>Armen presents…technical issues… torri shows some distributions that she gave to Armen. Armen resumes
 +
        <ul>
 +
            <li>Start by attempting to create a surrogate model
 +
                <ul>
 +
                    <li>GPR (like AIEC) to get polarization estimation</li>
 +
                    <li>Use cleaned data from Torri
 +
                        <ul>
 +
                            <li>Had to remove B_DAQ:HEL:60m:29:asycorr</li>
 +
                        </ul>
 +
                    </li>
 +
                </ul>
 +
            </li>
 +
            <li>Really good agreement
 +
                <ul>
 +
                    <li>Use std/mean for baseline etc and all other variables
 +
                        <ul>
 +
                            <li>cc*area is polarization…so maybe not use them…</li>
 +
                            <li>Some large error…need to investigate</li>
 +
                            <li>Looks like area was left out of input features</li>
 +
                        </ul>
 +
                    </li>
 +
                </ul>
 +
            </li>
 +
            <li>Discussion of the variables (e.g. cc and area)</li>
 +
            <li>ToDo:
 +
                <ul>
 +
                    <li>Test with area in input set</li>
 +
                    <li>Perform PCA on both models</li>
 +
                    <li>Do error propagation for the target values</li>
 +
                    <li>Histogram of the difference between the predictions and targets</li>
 +
                </ul>
 +
            </li>
 +
            <li>Torri asked for notebook access
 +
                <ul>
 +
                    <li>Will be given</li>
 +
                    <li>Model saved for posterity 🙂</li>
 +
                </ul>
 +
            </li>
 +
        </ul>
 +
    </li>
 +
    <li>Thomas will work with Patrick as a guinea pig for hands on</li>
 +
    <li>Torri is doing Abstracts for AIOP for CHEP</li>
 +
</ul>
  
 
==== Action Items ====
 
==== Action Items ====

Latest revision as of 17:58, 13 May 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
  3. Project Progress
  4. PIER Activities
    • Middle School Data Science Hackathon Workshop
    • HUGS mini-Workshop
  5. AOT



Minutes

  • Armen presents…technical issues… torri shows some distributions that she gave to Armen. Armen resumes
    • Start by attempting to create a surrogate model
      • GPR (like AIEC) to get polarization estimation
      • Use cleaned data from Torri
        • Had to remove B_DAQ:HEL:60m:29:asycorr
    • Really good agreement
      • Use std/mean for baseline etc and all other variables
        • cc*area is polarization…so maybe not use them…
        • Some large error…need to investigate
        • Looks like area was left out of input features
    • Discussion of the variables (e.g. cc and area)
    • ToDo:
      • Test with area in input set
      • Perform PCA on both models
      • Do error propagation for the target values
      • Histogram of the difference between the predictions and targets
    • Torri asked for notebook access
      • Will be given
      • Model saved for posterity 🙂
  • Thomas will work with Patrick as a guinea pig for hands on
  • Torri is doing Abstracts for AIOP for CHEP

Action Items