Hans Mikelson wrote:

>I think that perhaps a utility program would be useful for training the 
net.
>Perhaps there is a popular, publicly available, cross-platform ANN package
>which already exists.  If the Csound opcode were able to read this file
>format you could do the training in this "utility" program and then use the
>result in Csound.  Then you would not have to reinvent the wheel so much.

the only problem I see is that this utility program would need access to all 
the training data, so we could not be training the net with sonic material 
generated within csound
Thats why I was thinking more of a pair of ugens, a slow one that would be 
the training ugen, which would export the learned weights somewhere (a table 
or external file) and a 2nd ugen which would use this set of weights and 
just perform the response to whatever stimulus; this 2nd ugen would be very 
fast since all it had to do was calculate the net response

pedro