<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"><html><head><meta content="text/html;charset=UTF-8" http-equiv="Content-Type"></head><body ><div style="font-family: Verdana, Arial, Helvetica, sans-serif; font-size: 10pt;"><div><br></div>If you folks want the source and objects, I can get them to you via FTP.<br><br>I just copy-n-paste the html tables from the pages here: <a href="https://en.wikipedia.org/wiki/List_of_Greek_and_Latin_roots_in_English" target="_blank">https://en.wikipedia.org/wiki/List_of_Greek_and_Latin_roots_in_English</a><br><br>I pasted them into a class, then used a simple PEG grammar and PEG actor to extract the table rows into objects.<br><br>The objects are stored in Class Variable ordered collections, and from my experience, these are not transferrable via Monticello.<br><br>So any .mcz will have to re-run the (very fast) import process again.<br><br>Let me know, I will be happy to help.<br><br>t<br><br><br><div data-zbluepencil-ignore="true" style="" class="zmail_extra"><br><div id="Zm-_Id_-Sgn1">---- On Thu, 09 Apr 2020 00:32:40 -0400 <b>Herbert König <<a target="_blank" href="mailto:herbertkoenig@gmx.net">herbertkoenig@gmx.net</a>></b> wrote ----<br></div><br><blockquote style="border-left: 1px solid rgb(204, 204, 204); padding-left: 6px; margin: 0px 0px 0px 5px;"><div>Hi Stef,<br><br>great resource but I was too impatient to go through it. In the Nehmzow<br>book the SOMK is 1.5 pages including an image and ready to implement.<br>For training it uses distances instead of squared distances in the<br>article you mention (I just skimmed it for 5 minutes :-)) so that may<br>lead to faster convergence. Definitely worth a try and easy to<br>implement. Th usual thing with neural nets (and AI algorithms in<br>general) is you have to implement and try what works best for your problem.<br>Unless that changed since the last time I looked :-)<br><br>Very curious to see (and help) how it performs on the original problem<br>of this thread!<br><br>Cheers,<br><br>Herbert<br><br>Am 09.04.2020 um 01:36 schrieb Stéphane Rollandin:<br>>> <a target="_blank" href="https://dai.fmph.uniba.sk/courses/NN/haykin.neural-networks.3ed.2009.pdf">https://dai.fmph.uniba.sk/courses/NN/haykin.neural-networks.3ed.2009.pdf</a><br>><br>> This one seems very deep, and not the easiest ressource to start<br>> with... Maybe also have a look at this page:<br>><br>> <a target="_blank" href="https://www.superdatascience.com/blogs/the-ultimate-guide-to-self-organizing-maps-soms">https://www.superdatascience.com/blogs/the-ultimate-guide-to-self-organizing-maps-soms</a><br>><br>><br>> Stef<br>><br><br><br></div></blockquote></div><div><br></div></div><br></body></html>