Normalized column weight initialization function
W = randnc(S,PR)
randnc is a weight initialization function.
W = randnc(S,PR) takes two inputs,
Number of rows (neurons)
R-by-2 matrix of input value ranges = [Pmin Pmax]
and returns an S-by-R random matrix with normalized columns.
You can also call this in the form randnc(S,R).
A random matrix of four normalized three-element columns is generated:
M = randnc(3,4) M = -0.6007 -0.4715 -0.2724 0.5596 -0.7628 -0.6967 -0.9172 0.7819 -0.2395 0.5406 -0.2907 0.2747