Difference between revisions of "AIOP Dec. 9, 2024"

From epsciwiki
Jump to navigation Jump to search
 
(One intermediate revision by one other user not shown)
Line 55: Line 55:
 
# Project Progress
 
# Project Progress
 
#:
 
#:
−
#* Data mining/preparation
+
#* Simulation/Surrogate Model
 
#* [https://github.com/orgs/JeffersonLab/projects/18/ GitHub AIOP Project] ''([https://github.com/JeffersonLab/AIOP-Target/issues AIOP-Target issues])''
 
#* [https://github.com/orgs/JeffersonLab/projects/18/ GitHub AIOP Project] ''([https://github.com/JeffersonLab/AIOP-Target/issues AIOP-Target issues])''
 
#:
 
#:
Line 70: Line 70:
  
 
=== Minutes ===
 
=== Minutes ===
 +
<h1>AIOP Target 12-9-24</h1>
 +
    <h2>Attendees</h2>
 +
    <ul>
 +
        <li>David</li>
 +
        <li>Thomas</li>
 +
        <li>Torri</li>
 +
        <li>Naomi</li>
 +
        <li>Malachi</li>
 +
        <li>Jiawei</li>
 +
        <li>Armen</li>
 +
    </ul>
  
 +
    <h2>Progress</h2>
 +
    <ul>
 +
        <li>AI in NP PI exchange report</li>
 +
        <li>CHEP proceedings project created on Overleaf</li>
 +
        <li>
 +
            Torri showed the progress on the simulation, including the web-based GUI.
 +
            Polarization is depolarizing too fast.
 +
            <ul>
 +
                <li>Malachi mentioned the need for differentiability.
 +
                    <ul>
 +
                        <li>Armen will help Torri with this.</li>
 +
                    </ul>
 +
                </li>
 +
                <li>David dug into the parameters:
 +
                    <ul>
 +
                        <li>Initial T1 (spin lattice relaxation time) is the most important.</li>
 +
                    </ul>
 +
                </li>
 +
                <li>Suggestions were made to make it more realistic (on top of being fundamentally "correct").</li>
 +
                <li>David inquired about how difficult it would be to implement the simulation.
 +
                    <ul>
 +
                        <li>Armen: Maybe.</li>
 +
                        <li>Torri is the "bottleneck" due to simulation complexity. Torri needs to sit down with James.</li>
 +
                    </ul>
 +
                </li>
 +
            </ul>
 +
        </li>
 +
        <li>Armen will work on a surrogate model.</li>
 +
        <li>
 +
            David asked for the "reliability plot" (currently quite underconfident).
 +
        </li>
 +
    </ul>
 +
 +
    <h2>Action Items</h2>
 +
    <ul>
 +
        <li>Armen to assist Torri with ensuring the simulation supports differentiability.</li>
 +
        <li>Torri to meet with James to address simulation complexity issues.</li>
 +
        <li>David to refine and evaluate the reliability plot.</li>
 +
        <li>Armen to develop a surrogate model for the simulation.</li>
 +
    </ul>
  
 
==== Action Items ====
 
==== Action Items ====

Latest revision as of 18:43, 9 December 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. Conferences/Workshops
    • NP AI PI Exchange Meeting (Dec. 4-5 Washington D.C.)(David, Thomas, Naomi)
  4. Project Progress
  5. PIER Activities
    • Middle School Data Science Hackathon Workshop (Oct. 16) Flappy Bird RL Learning - COMPLETED!
    • HUGS mini-Workshop - COMPLETED!
  6. AOT


Minutes

AIOP Target 12-9-24

Attendees

  • David
  • Thomas
  • Torri
  • Naomi
  • Malachi
  • Jiawei
  • Armen

Progress

  • AI in NP PI exchange report
  • CHEP proceedings project created on Overleaf
  • Torri showed the progress on the simulation, including the web-based GUI. Polarization is depolarizing too fast.
    • Malachi mentioned the need for differentiability.
      • Armen will help Torri with this.
    • David dug into the parameters:
      • Initial T1 (spin lattice relaxation time) is the most important.
    • Suggestions were made to make it more realistic (on top of being fundamentally "correct").
    • David inquired about how difficult it would be to implement the simulation.
      • Armen: Maybe.
      • Torri is the "bottleneck" due to simulation complexity. Torri needs to sit down with James.
  • Armen will work on a surrogate model.
  • David asked for the "reliability plot" (currently quite underconfident).

Action Items

  • Armen to assist Torri with ensuring the simulation supports differentiability.
  • Torri to meet with James to address simulation complexity issues.
  • David to refine and evaluate the reliability plot.
  • Armen to develop a surrogate model for the simulation.

Action Items

Retrieved from "https://wiki.jlab.org/epsciwiki/index.php?title=AIOP_Dec._9,_2024&oldid=5899"