I haven't actually read all this post yet, but just thought I would
mention the one music-related n-network project I know of: at Bristol
'Digital  Music Research' group, doing feature extraction:


http://www.fen.bris.ac.uk/elec/research/ccr/dmr/news3.html

their site has not been updated for a while, so they may be further on
than they indicate.

I have been passively interested in n-nets ever since I was given the
opportunity to review 'Music and Connectionism'.

I would think Csound is not really ideally suited to ~researching~ n-net
algorithms (or training them), any more than you would want to code an
fft in it step by step; but a fully-trained net implemented as an opcode
should be able to run in Csound on a decent machine. So the interesting
question is - how would that be implemented. It is a plugin opcode, but
with a difference!


Richard Dobson


jpff@maths.bath.ac.uk wrote:
> 
> Message written at 31 Mar 1999 16:26:28 +0530
> 
> ------- Start of forwarded message -------
> Date: 29 Mar 99 08:56 GMT
> Priority: normal
> P1-Message-ID: pt*mailpac*gtw-ms;0922697806/0077436395/1
> Original-Encoded-Information-Types: IA5-Text
> From: Pedro Batista 
> To: j.p.ffitch@maths.bath.ac.uk
> Subject: Re: neural nets
> 
> __________________
> 
> >>do you have any ideas of what exactly you'll use the network for?
> >
> >Good point and maybe it isn't worth the effort although there are some
> >people who claim to be doing some interesting things with them.  Check out
> 
> Surely there are a number of interesting projects around! 

-- 
Test your DAW with my Soundcard Attrition Page!
http://wkweb5.cableinet.co.uk/rwd