Hello,

I am trying to work out a neural network in pd. I am a bit overwhelmed by some of the math and how you would enter it in the [expr] object. I have presumably figured out how to get the error of a network segment using the mean squared error (http://en.wikipedia.org/wiki/Mean_squared_error) which is shown in the patch.

My struggles come when I try to get the output from the network using the sigmoid function (

If anyone can help please do.

Thanks guys!

http://www.pdpatchrepo.info/hurleur/Neural_network.pd

Well I found this some time ago

http://fredvoisin.com/web/spip.php?article159

It's a neuron implementation, and a nn but without any learning formula, maybe that will help you.