What does fitnet (or the neural network toolbox) do if you give it more than 1 target?

how does fitnet handle a target with, say, 3 differnet parameters for N samples [3 N] with an x*N-Input? Does it calculate the targets the same as if it was training three independent nn's for each target-parameter, or does the output for one target-parameter influence the other two and vice versa?

is there a way to establish a relationship between the three target vlaues (such as sum(target)=1) that the neural network recognizes and uses as a constraint to the output values, or for that matter a way to apply a constraint to the output values directly?

Thank you for your answer, F