Apparently, a target variance of 9e10 is too much for feedforwardnet to handle. Standardization(zero-mean/unit-variance) does the trick!
close all, clear all, clc
x = 0:1:1000 ; t = x.^2 + 1;
vart1 = var(t,1)
zx = zscore(x,1); zt = zscore(t,1);
net = feedforwardnet( 10, 'traingd' );
rng('default')
for i = 1:10
net = configure( net, zx, zt );
net = train( net, zx, zt );
NMSE( i ) = mse( zt - net( zx ) );
end
NMSE = NMSE
Hope this helps.
Thank you for formally accepting my answer
Greg
Best Answer