there was a porting going on, but it then stopped for some reasons which I personally don't know, but I think have been on the list at some point.<br><br>Me and other people, like Joao Pais, are interested in making the porting happen, and as we can see, there's demand for it.<br>
<br><br clear="all"><div>--<br>Marco Donnarumma<br>New Media + Sonic Arts Practitioner, Performer, Teacher, Director.<br>Embodied Audio-Visual Interaction Research Team.<br>Department of Computing, Goldsmiths University of London<br>
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~<br>Portfolio: <a href="http://marcodonnarumma.com" target="_blank">http://marcodonnarumma.com</a><br>Research: <a href="http://res.marcodonnarumma.com" target="_blank">http://res.marcodonnarumma.com</a><br>
Director: <a href="http://www.liveperformersmeeting.net" target="_blank">http://www.liveperformersmeeting.net</a></div><br>
<br><br><div class="gmail_quote">On Mon, Dec 17, 2012 at 10:59 AM, Leandro da Mota Damasceno <span dir="ltr"><<a href="mailto:lemota@gmail.com" target="_blank">lemota@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
I'll try it then. I wonder there isn't a more ambitious approach for a broader AI package for PD. Honestly, one of the ugliest things I've done to work with machine learning was running an app built in Max/MSP and communicating with PD via OSC. Ah, the good old days... :)<br>
<br>is there anything like FTM for PD?<div class="HOEnZb"><div class="h5"><br><div class="gmail_extra"><br><br><div class="gmail_quote">On Mon, Dec 17, 2012 at 1:39 PM, Marco Donnarumma <span dir="ltr"><<a href="mailto:devel@thesaddj.com" target="_blank">devel@thesaddj.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Probably :)<br><br>ANN is based on Neural Networks. You don't have HMM.<br>But I find it quite flexible.<br>That said, I think it is a very good library to get started with AI, but if you want to get some heavy work done, other tools might be better.<br>
<br>hope that helps,<div><br><br clear="all"><div>--<br>Marco Donnarumma<br>New Media + Sonic Arts Practitioner, Performer, Teacher, Director.<br>Embodied Audio-Visual Interaction Research Team.<br>Department of Computing, Goldsmiths University of London<br>
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~<br>Portfolio: <a href="http://marcodonnarumma.com" target="_blank">http://marcodonnarumma.com</a><br>Research: <a href="http://res.marcodonnarumma.com" target="_blank">http://res.marcodonnarumma.com</a><br>
Director: <a href="http://www.liveperformersmeeting.net" target="_blank">http://www.liveperformersmeeting.net</a></div><br>
<br><br></div><div><div><div class="gmail_quote">On Mon, Dec 17, 2012 at 6:50 AM, Leandro da Mota Damasceno <span dir="ltr"><<a href="mailto:lemota@gmail.com" target="_blank">lemota@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Thanks, Marco. I have been using OSC communications with other software, but I'm far from satisfied. I'll try ANN, thought.<div><br></div><div>I am actually interested in working with Hidden Markov Models (and machine learning in general) and some filters for computer vision. Can I work with those using ANN?</div>
<div><br></div><div>Best,</div><div><br></div><div>Leandro</div><div><div><div class="gmail_extra"><br><br><div class="gmail_quote">On Sun, Dec 16, 2012 at 11:23 PM, Marco Donnarumma <span dir="ltr"><<a href="mailto:devel@thesaddj.com" target="_blank">devel@thesaddj.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hey,<br><br>I've been using the ANN library. <br>I'm not sure it's still updated nor mantained these days, but it does work well for my purpose.<br>
<br><a href="http://puredata.info/search?SearchableText=ann" target="_blank">http://puredata.info/search?SearchableText=ann</a><br>
<br>That is, I've been using it to make my instrument (the Xth Sense [1]) detect a performer's muscle states throughout a piece by using 1 sensor only; then, labelling different states, such as still, motion, fast motion, slow motion. It's a basic implementation but useful to create a sensing timeline that changes with the performer behaviours, rather than with fixed time cues.<br>
<br>Surely, there is much more to AI which cannot be presently done in Pd, at the best of my knowledge, I might be wrong though.<br>Ben (Bogart) is our guy in this area. <br><br>What are you using Ben?<br><br>[1] <a href="http://res.marcodonnarumma.com/projects/xth-sense/" target="_blank">http://res.marcodonnarumma.com/projects/xth-sense/</a><div>
<div><br>
<br><br style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex" class="gmail_quote"><blockquote><blockquote style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex" class="gmail_quote">
Hi all<br><br>
I have been wondering... Is there any AI implementation for PD? What have you been using for it?<br><br>
Best<br><br>
Leandro</blockquote></blockquote>
</div></div><div>--<br>Marco Donnarumma<br>New Media + Sonic Arts Practitioner, Performer, Teacher, Director.<br>Embodied Audio-Visual Interaction Research Team.<br>Department of Computing, Goldsmiths University of London<br>
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~<br>
Portfolio: <a href="http://marcodonnarumma.com" target="_blank">http://marcodonnarumma.com</a><br>Research: <a href="http://res.marcodonnarumma.com" target="_blank">http://res.marcodonnarumma.com</a><br>Director: <a href="http://www.liveperformersmeeting.net" target="_blank">http://www.liveperformersmeeting.net</a></div>
<br>
</blockquote></div><br></div>
</div></div></blockquote></div><br>
</div></div></blockquote></div><br></div>
</div></div></blockquote></div><br>