Is there any method to find out the number of layers and the number of neurons per layer? As input I solely have the size of the input vector, the size of the output vector and the size of the training set.

We can find out the best net by trying different net topologies and choosing among the one with the least error. Unfortunately I can't try this.

We can find out the best net by trying different net topologies and choosing among the one with the least error. Unfortunately I can't try this.