Automatic differentiation

[prcastro]

This is what Theano do when used in Deep Learning with Python. We can do it by using packages from JuliaDiff to compute the derivatives instead of using a derivative dictionary. While this could cause some slowdown on differentiation (and at import, because we would depend on a package), this wouldn't be much, and would make much easier to extend the library with new cost/activation functions.

[prcastro]

This would probably mean that activation functions would have to be defined as functions of vectors, and not of FFNNLayers