<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Hi all,<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
I've put together a quick example on using machine learning for PID in java using the deeplearning4j library. You can find this example at
<a href="https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_rtysonCLAS12_ML-5Fnotebooks_tree_main_DL4J-5FExample&d=DwMFAg&c=CJqEzB1piLOyyvZjb8YUQw&r=p0fOsYOqPes7kSrF0-ldLy8UQdwZWwpYV125WHZsrFE&m=BwBbsEIDFWV-OefkX_wIaWj4lMaKJ-eSyVzXsEJgIRg&s=BaKvatiCs03nvCNd2BvQmD-g7OlyzwJUnZInCUyilfc&e=" id="LPlnk995142">
https://github.com/rtysonCLAS12/ML_notebooks/tree/main/DL4J_Example</a> . Unfortunately, I'm not that familiar with computing at JLab (or with maven/eclipse) so it would be nice if anyone wanting to learn how to use these tools could try running this by Friday
and let me know how they got on! In principle theDL4J_Example repository is an eclipse-workspace so I'm hoping that it won't be too hard to import the maven project it houses (but again would be great to get feedback on this)...
<br>
<br>
I've also recently given a seminar for our group in Glasgow for which I put together a short example on using machine learning for denoising toy drift chamber data in python, you can try this out following the instructions in the attached slide, it takes 5
minutes. I'd be happy to also discuss this on Friday if people are interested, although I realise we might not have enough time for all this.<br>
<br>
Thanks,<br>
Richard<br>
<br>
</div>
<div id="appendonsend"></div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" style="font-size:11pt" color="#000000"><b>From:</b> Clas12_rgb <clas12_rgb-bounces@jlab.org> on behalf of silvia@jlab.org <silvia@jlab.org><br>
<b>Sent:</b> 13 June 2021 20:13<br>
<b>To:</b> clas12_rgb@jlab.org <clas12_rgb@jlab.org><br>
<b>Subject:</b> [Clas12_rgb] machine-learning tutorial at the next RGB meeting</font>
<div> </div>
</div>
<div class="BodyFragment"><font size="2"><span style="font-size:11pt;">
<div class="PlainText">Dear all,<br>
following Adam's presentation on the machine-learning-based veto for<br>
protons in the CD, and given the interest of the people attending, we<br>
decided to devite our next RG-B meeting (Friday June 18th, 8:30AM) to a<br>
"tutorial" session on machine learning. It will be hosted by Adam (for the<br>
ROOT-based tutorial) and Richard (for the Java-based tutorial). It will be<br>
a very practical session, to teach how to use the available codes and get<br>
operational quickly.<br>
I think this can be a nice first step towards the sharing of analysis<br>
tools, at least within RG-B - although if anyone from other RG's is<br>
reading this message, they'll be very welcome as well.<br>
I may actually inform the WG leaders of this tutorial session to see if<br>
they think it could be beneficial to advertise it to their groups.<br>
Best regards,<br>
Silvia<br>
<br>
<br>
_______________________________________________<br>
Clas12_rgb mailing list<br>
Clas12_rgb@jlab.org<br>
<a href="https://mailman.jlab.org/mailman/listinfo/clas12_rgb">https://mailman.jlab.org/mailman/listinfo/clas12_rgb</a><br>
</div>
</span></font></div>
</body>
</html>