initialization of a neural network with 1 hidden layer, with bias
[wh,wo]=nns_init(x,y,(options))
calibration dataset
x is a matrix of dimensions (n x q) or a Div structure
reference values, to be predicted
y is a matrix of dimensions (n x no) or a Div structure
number of hidden neurons (by default = 5)
method of initialization
method='l': linear model for the first neuron, random small value for the following
method='n': Nguyen-Widrow (by default)
method='r': random values of small variance
coefficients of the hidden neurons + bias
wh is a matrix of dimensions ((q+1) x nh) or a Div structure
nh is the number of hidden neurons
coefficients of the output neurons + bias
wo is a matrix of dimensions ((nh+1) x no) or a Div structure
no is the number of output neurons