I was wondering: a) Does having multiple hidden layers require an exponential amount of training, and how much does it increase accuracy? b) which functions(sigmoid, etc) do you use?

a) I would assume so, but I'm still working on my backpropagating network, so I can't give you any numbers as of yet!

b) I use a simple step limiting function for single neurons, as it only needs to be differenciable for multi-layer networks, and it doesn't give "messy" numbers like the Sigmoid function.

For everything else so far, though, I've used the Sigmoid function because it's cleaner than everything else I've come across! and it's range is limited to {0, 1} which is so very helpful when teaching boolean operations.