Hi,

Pedro wrote:
>wouldnt you rather have the code in C so that you could do whatever you
>wanted without depending on 3rd party sw?

Umm, yes, maybe my original thought was to avoid some of the dirty work like
training algorithms and just interpret the trained network in Csound.

>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
Prosoniq:

http://www.prosoniq.com/

They supposedly use neural networks in Pandora, which claims to use a
virtual hearing algorithm.  It seems I've heard of them being used for
formant peak identification, pitch shifting and reverb removal.

>I did, if you remember, but I didnt seem to get your interest

You got my interest but it just took me a while to get around to working on
this.

You're right about me making some wrong assumptions, I've been reading about
neural networks a bit more and some of my original assumptions were way off
base.  What I need to do is experiment with them for a while to see what
useful things can be done with neural nets.  Then try and figure out what
the most useful form of an opcode would be.  I will review your earlier
comments concerning this.  I thought it might be useful to write some
temporary opcodes for experimenting though to make things easier.

I got the Stuttgart package working and trained their demo network with it
now, so I understand a little more about what the network is doing.  I had
forgotten that neurons are binary so as far as I can tell it must take a
bunch of neurons to do anything useful.

Still learning,
Hans Mikelson