MAE = getMAE(x,y)

Computes the Mean Absolute Error (MAE) between two vectors x and y of same length.

INPUT :

x : can be a function Interpolating the data points in 'y'. It is a < N y 1 > vector, typically resulting
from the application of 'polyfit' and 'polyval' functions.

y : can be observed data points for which I want to find the best-fitting function
(i.e. minimizing MAE, but avoiding overfitting). it's a < N y 1 > vector


OUTPUT :

MAE : Mean Absolute Error (a scalar).