Addition of new input/output neurons to an existing trained NN

[Samir S]

I am analyzing whether Neural Networks will be able to handle our current
classification problems, with varying input and output data- types (not
necessarily all types being known at time of NN creation).

Does FANN allow this, wherein we can add input neurons to an existing NN.
Let's say I have trained a NN to learn about 2 input data types (d1 and d2)
with outputs o1 and o2 Is it possible to further train this NN to now handle
additional input data type (d3) and additional output o3 nodes. Is it even
theoretically possible ? Of course, I don't want to re-build or re-train the
entire network to handle such a scenario.

Thanks in advance
Samir