Difference between revisions of "AI tutorials"

From GlueXWiki
Jump to: navigation, search
(→‎Agenda)
 
(43 intermediate revisions by 9 users not shown)
Line 7: Line 7:
 
* Performance evaluation --> ROC-Curve, confusion matrix, accuracy, loss curves,...
 
* Performance evaluation --> ROC-Curve, confusion matrix, accuracy, loss curves,...
 
* Visualization --> How to properly present the performance of a model ? What are "good" diagnostic plots ?  
 
* Visualization --> How to properly present the performance of a model ? What are "good" diagnostic plots ?  
−
* Model deployment --> How to use a model within the GlueX analysis software
 
 
* Data fed into models --> What data sets are used ? Numerical, vs. Images, raw data vs. clean data,...  
 
* Data fed into models --> What data sets are used ? Numerical, vs. Images, raw data vs. clean data,...  
−
* Tools made available by the data science department
 
 
* Optional, depending on time: HPO --> Tune the parameters of your model
 
* Optional, depending on time: HPO --> Tune the parameters of your model
−
* Optional, depending on time: Bookkeeping of models via MLFlow
+
* Optional, depending on time: Different network architectures
  
 
= Location and Time =
 
= Location and Time =
Line 24: Line 22:
  
 
= Remote Participation =
 
= Remote Participation =
 +
 +
Zoom link can be found below:
  
 
<div class="toccolours mw-collapsible mw-collapsed">
 
<div class="toccolours mw-collapsible mw-collapsed">
 +
 +
https://jlab-org.zoomgov.com/j/1606473787?pwd=djJheGhRY0o1RENMVkdkMnhrUUZEUT09
  
 
</div>
 
</div>
Line 40: Line 42:
 
= Workshop Software =
 
= Workshop Software =
  
−
[https://halldweb.jlab.org/wiki/index.php/File:Pid_example_v0.ipynb PID example Notebook]
+
* Google online jupyther notebook: https://colab.google/
 +
 
 +
[https://jupyter.org/install Install jupyter on your linux machine]
 +
 
 +
[https://www.geeksforgeeks.org/install-jupyter-notebook-in-windows/ install-jupyter-notebook-in-windows]
 +
 
 +
Daniel's example:
 +
 
 +
* [https://halldweb.jlab.org/wiki/index.php/File:Pid_example_v0.ipynb PID example Notebook]
  
 
= Agenda =
 
= Agenda =
Line 48: Line 58:
 
<b>Feb 18</b>
 
<b>Feb 18</b>
  
−
* 09:00 Welcome (5min)
+
* 09:00 [https://halldweb.jlab.org/wiki/images/b/bd/Welcome.pdf Welcome] (5min)
−
* 09:05 Brief introduction to Machine and Deep Learning (1h35)  
+
* 09:05 [https://halldweb.jlab.org/wiki/index.php/File:Gluex_AI_workshop_feb2025_dlersch.pdf Brief introduction to Machine and Deep Learning] (Daniel Lersch - 1h35)  
 
* 10:40 Break (20 min)
 
* 10:40 Break (20 min)
−
* 11:00 Notebook setup (15min)  
+
* 11:00 [https://halldweb.jlab.org/wiki/images/d/d6/Notebook-setup.pdf Notebook setup] (15min)  
−
* 11:15 Data preparation and feature engineering (1h15)
+
* 11:15 [https://halldweb.jlab.org/wiki/images/2/2a/ML_Conference.pdf Data preparation and feature engineering] (Anupam Siwakoti - 1h15)
 
* 12:30 Lunch (1 h)
 
* 12:30 Lunch (1 h)
−
* 13:30 Setting up a model and training it (1h15)
+
* 13:30 [https://halldweb.jlab.org/doc-private/DocDB/ShowDocument?docid=6737  Setting up a model and training it] (Anupam Siwakoti/ Zach Baldwin - 1h15)
−
* 14:45 Final performance evaluation (1h15)
+
* 14:45 [https://halldweb.jlab.org/doc-private/DocDB/ShowDocument?docid=6736 Final performance evaluation] (Zach Baldwin - 1h15)
−
* 16:00 Break (20min)
+
* 16:00 Break (30min)
−
* 16:30 HYDRA (45min)
+
* 16:30 [https://docs.google.com/presentation/d/1EPkUalsHw-WC2ghkUhmoV6LHUNJQ7OT-L43pss4GLJk/edit?usp=sharing AI: Data Quality Monitoring] (Thomas Britton - 30min)
  
 
<b>Feb 19</b>
 
<b>Feb 19</b>
  
−
* 09:40 TMVA (30min)
+
* 09:30 [[media:Aschick19.2.2025.TMVATutorial.pdf |A TMVA example (Andrew Schick - 1h)]]
−
* 10:10 TMVA (30min)
+
* 10:30 Break (20min)
−
* 10:40 Break (20min)
+
* 10:50 [https://halldweb.jlab.org/wiki/index.php/File:GlueX_AI_workshop.pptx Graph Neural Network] (Ahmed Mohammed - 30min)
−
* 11:00 Graph Neural Network (45min)
+
* 11:20 [https://halldweb.jlab.org/wiki/images/1/1a/ThankYou.pdf Thank you] (5min)
  
 
&nbsp;
 
&nbsp;
Line 72: Line 82:
 
Please add your name to the list of attendees below. No formal registration or registration fee is required.
 
Please add your name to the list of attendees below. No formal registration or registration fee is required.
  
−
{
+
{| border="1" cellpadding="2" valign="top" style="text-align: center;"
−
| border="1" cellpadding="2" valign="top" style="text-align: center;"
+
 
!width="180"| Name
 
!width="180"| Name
 
!width="200"| Home Institution
 
!width="200"| Home Institution
Line 83: Line 92:
 
| Daniel || JLab || Staff || Yes
 
| Daniel || JLab || Staff || Yes
 
|-
 
|-
−
| Gyang || Virginia Tech || Student || Yes
+
| Gyang || Virginia Tech || Student || No
 
|-
 
|-
 
| Karthik || William and Mary || Postdoc || No
 
| Karthik || William and Mary || Postdoc || No
Line 117: Line 126:
 
|Vitor Shen || Ruhr University Bochum || Graduate Student || No
 
|Vitor Shen || Ruhr University Bochum || Graduate Student || No
 
|-
 
|-
−
}
+
| Kevin Saldaña || Indiana University || Graduate Student || Yes
−
&nbsp;
+
|-
 +
| Daniel Barton || Old Dominion University || Graduate Student || Yes
 +
|-
 +
| Alex Berger || Glasgow University || Student || Yes
 +
|}
 +
 
  
 
= Recording =
 
= Recording =

Latest revision as of 12:43, 19 February 2025

Purpose

The overall topic is: „Best practice for AI in nuclear physics applications“. We wish to cover the following items via plenary talks and/or interactive tutorials:

  • Feature engineering --> Feature normalization, correlation coefficients, feature selection, etc.
  • Overfitting --> Dropout layers, weight regularization, etc.
  • Performance evaluation --> ROC-Curve, confusion matrix, accuracy, loss curves,...
  • Visualization --> How to properly present the performance of a model ? What are "good" diagnostic plots ?
  • Data fed into models --> What data sets are used ? Numerical, vs. Images, raw data vs. clean data,...
  • Optional, depending on time: HPO --> Tune the parameters of your model
  • Optional, depending on time: Different network architectures

Location and Time

The workshop will take place at:

DATES: February 18 (all day) - 19 (morning only), 2025

LOCATION: CEBAF Center F113

 

Remote Participation

Zoom link can be found below:

https://jlab-org.zoomgov.com/j/1606473787?pwd=djJheGhRY0o1RENMVkdkMnhrUUZEUT09


 

References

 

Workshop Software

Install jupyter on your linux machine

install-jupyter-notebook-in-windows

Daniel's example:

Agenda

AI Tutorials

Feb 18

Feb 19

 

Registration

Please add your name to the list of attendees below. No formal registration or registration fee is required.

Name Home Institution Level Participate at JLab
ig JLab Staff Yes
Daniel JLab Staff Yes
Gyang Virginia Tech Student No
Karthik William and Mary Postdoc No
Zachary Baldwin Carnegie Mellon University Graduate Student Yes
Nizar Septian Florida State University Student Yes
Alex Austregesilo JLab Staff Yes
Drew Smith JLab Postdoc Yes
Sean Dobbs FSU Faculty Yes
Will Imoehl Carnegie Mellon University Postdoc No
Farah Afzal Ruhr University Bochum Faculty Yes
Peter Hurck Glasgow Faculty Yes
Lawrence Ng JLab Postdoc Yes
Albert Fabrizi University of Mass. Amherst Graduate Student Yes
Shannen Graham-Howard University of Mass. Amherst Graduate Student Yes
Jiawei Guo Carnegie Mellon University Graduate Student Yes
Boris Grube JLab Staff Yes
Churamani Paudel FIU Postdoc No
Vitor Shen Ruhr University Bochum Graduate Student No
Kevin Saldaña Indiana University Graduate Student Yes
Daniel Barton Old Dominion University Graduate Student Yes
Alex Berger Glasgow University Student Yes

 

Recording

Retrieved from "https://halldweb.jlab.org/wiki/index.php?title=AI_tutorials&oldid=128751"