Kohonen (example from help does not work)

2 vues (au cours des 30 derniers jours)
Alexander
Alexander le 7 Sep 2011
Hi all, please I need your help !
example (Kohonen) from help does not work
>> p = [.1 .8 .1 .9; .2 .9 .1 .8];
>> net = newc([0 1; 0 1],2);
>> wts = net.IW{1,1}
>> biases = net.b{1};
>> net.trainParam.epochs = 500;
>> net = train(net,p);
>> a = sim(net,p);
>> ac = vec2ind(a); >> ac
ac =
1 1 1 1
>> wts
wts =
0.5000 0.5000
0.5000 0.5000
My weight did not change. in example
wts =
0.1000 0.1467
0.8474 0.8525
Maybe I'm doing something wrong?

Réponse acceptée

Alexander
Alexander le 8 Sep 2011
7.10.0 (R.2010b)
  1 commentaire
Lucas García
Lucas García le 8 Sep 2011
So, download the fix in the previous link and give it a try. Then it will work fine.

Connectez-vous pour commenter.

Plus de réponses (3)

Walter Roberson
Walter Roberson le 7 Sep 2011
You did not assign a new value to wts, so it is going to continue to be the value that was retrieved before you did the training. You need to retrieve net.IW{1,1} after the training in order to see the effect of the training on the weights.
  1 commentaire
Alexander
Alexander le 8 Sep 2011
These are my values after training
net.IW{1,1}
ans =
0.5000 0.5000
0.5000 0.5000
After training, they have not changed.

Connectez-vous pour commenter.


Lucas García
Lucas García le 8 Sep 2011
Which release are you using? There is a known bug in R2010b and R2011a regarding newc and competlayer.
It has been fixed in R2011b.
  1 commentaire
Alexander
Alexander le 12 Sep 2011
Thanks Men. You saved my life !!! :)))

Connectez-vous pour commenter.


Alexander
Alexander le 8 Sep 2011
It is strange, but FIX_R2010b_COMPETLAYERAYER.zip is corrupted.
FIX_R2011a_COMPETLAYER.zip is normal.

Catégories

En savoir plus sur Sequence and Numeric Feature Data Workflows dans Help Center et File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by