Prev: imwrite error in saving to a folder
Next: how to vecotrize this?
From: a a on 2 Jul 2010 05:37
Hello,

I'm running into some problems with the adapt function. I copied in the example that is found in 'help adapt' and the function does not seem to minimize the error.

Given:
p1 = {-1 0 1 0 1 1 -1 0 -1 1 0 1};
t1 = {-1 -1 1 1 1 2 0 -1 -1 0 1 1};

net = newlin([-1 1],1,[0 1],0.5);
[net,y,e,pf] = adapt(net,p1,t1);
mse(e)

p2 = {1 -1 -1 1 1 -1 0 0 0 1 -1 -1};
t2 = {2 0 -2 0 2 0 -1 0 0 1 0 -1};
[net,y,e,pf] = adapt(net,p2,t2,pf);
mse(e)

p3 = [p1 p2];
t3 = [t1 t2];
net.adaptParam.passes = 100;
[net,y,e] = adapt(net,p3,t3);
mse(e)
-- The three mse(e) displays read:

ans = 0.3374
ans = 0.0828
ans = 0.1039
If I increase net.adaptParam.passes = 10000, I still get 0.1039 as the mean squared error.

Is this what others get, or is something wrong with the way the function is operating on my machine?

Thanks!
 | 
Pages: 1
Prev: imwrite error in saving to a folder
Next: how to vecotrize this?