<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<small>Hi Christian,<br>
<br>
thanks for the reply. I'm on a very similar boat regarding
machine learning as you.<br>
<br>
What I'm interested in is AGI (Artificial General Inteligence),
where the machine learning is general (not specialized and limited
in some kind of way). I was thinking to make a small application
which I could train for example to communicate with me (simulate
grow development). Later I would go ahead with some simple
tasks,...etc.<br>
<br>
So far I thought that behind will be some modification of
reinforcement and evolutionary learning. Knowledge/data will be in
graph DB (what seems that it would need to be done by me/us? :-) )</small>
<small><br>
<br>
Let me know if this sounds interesting for you.<br>
<br>
Cheers,<br>
Miro</small><br>
<br>
On 18.05.2012 13:21, C Gosch wrote:
<blockquote
cite="mid:CAJ5UeeXCdgf8R=T5xKAbUFXy-vDXy4eqgbYK8JeCd0RJAzKs4A@mail.gmail.com"
type="cite">
<pre wrap="">Hi all,
I have implemented max-sum/sum-product in c++ before and a while ago,
did the same in Haskell.
I don't think my implementation is as idiomatic Haskellish as I would
like, and I have so far not
published it and also not looked at it for a little while (since I
have some more projects :) ).
However, if you are interested, I will publish it (maybe on github?),
and I think we should join forces.
I am also very interested in machine learning techniques, but I can
unfortunately use neither those nor Haskell at
my day job at present.
Let me know what you think.
Best regards,
Christian
Message: 3
Date: Thu, 17 May 2012 15:36:08 +0400
From: Paul Graphov <a class="moz-txt-link-rfc2396E" href="mailto:graphov@gmail.com"><graphov@gmail.com></a>
Subject: Re: [Haskell-cafe] AI - machine learning
To: miro <a class="moz-txt-link-rfc2396E" href="mailto:miroslav.karpis@gmail.com"><miroslav.karpis@gmail.com></a>
Cc: <a class="moz-txt-link-abbreviated" href="mailto:haskell-cafe@haskell.org">haskell-cafe@haskell.org</a>
Message-ID:
<a class="moz-txt-link-rfc2396E" href="mailto:CAKHAQn+yFGCdLPoKR0sEhvJobwPPykvqTYieqZeBbzhyVodizg@mail.gmail.com"><CAKHAQn+yFGCdLPoKR0sEhvJobwPPykvqTYieqZeBbzhyVodizg@mail.gmail.com></a>
Content-Type: text/plain; charset=UTF-8
Hi Miro!
I have no useful information for you. Few weeks ago I also checked for
any AI (machine learning first of all) related packages exist and
found nothing satisfactory except for some quite small packages
implementing a single algorithm (like NN-back-propagation). So there
is a lot to do :)
If you are going to do something in this area please let me know, I'll
be glad to collaborate!
p.s. Now I'm taking Machine Learning course at Coursera.org and
looking forward to apply this knowledge with Haskell.
On Tue, May 15, 2012 at 3:02 AM, miro <a class="moz-txt-link-rfc2396E" href="mailto:miroslav.karpis@gmail.com"><miroslav.karpis@gmail.com></a> wrote:
</pre>
<blockquote type="cite">
<pre wrap="">Hi All, recently I started to take a look at haskell, especially at AI. I
can see some email addresses of interested people there but not so much of
other activity behind. Does it exist some mailing group especially for AI?
Basically I'm interested in trying some machine learning algorithms. Start
with reinforcement learning and value-based), and go towards AGI (Artificial
General Intelligence). Does anybody know about some already existing haskell
approaches, or is there anybody working on this?
Cheers,
m.
</pre>
</blockquote>
</blockquote>
<br>
</body>
</html>