I'm currently working on a neural network that should have $N$ parameters in input. Each parameters can have $M$ different values (discrete values), let's say $\{A,B,C,\dotsc,M\}$. It also has a discrete number of outputs.
How can I create my inputs from this situation? Should I have $N \times M$ inputs (having $0$ or $1$ as value), or should I think of a different approach?