Question: Just Getting Started with NARX NN
8 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Hi.
Just getting into the NN Toolbox. I have an error with PREPARETS that I don't full understand.
Context of the environment: inputs--> 4x1500 and outputs--> 1x1500
x=inputs;
t=outputs;
net = narxnet(1:2,1:2,10,'open','trainbr')
[X,Xi,Ai,T] = preparets(net,x,{},t);
net = train(net,X,T,Xi,Ai);
view(net)
Y = net(X,Xi,Ai)
perf = perform(net,Y,T)
Error:
Index exceeds matrix dimensions.
Error in preparets (line 293) xi = xx(:,FBS+((1-net.numInputDelays):0));
Error in cup (line 5) [X,Xi,Ai,T] = preparets(net,x,{},t);
Since I'm starting out with the NNTOOL box, I wanted go simple. It surprised me that I get an error with the simple example code referenced in the help guide.
My gut says that I have not aligned the default function inputs with the array size of my data.
But I'm open to feedback and steer from others.
Thanks
0 commentaires
Réponses (1)
Greg Heath
le 3 Déc 2017
IN ORDER OF PREFERENCE, the best way to get help is
1a. Demonstrate with the MATLAB help or doc dataset example
help narxnet
doc narxnet
or a minor modification (e.g., 4 inputs)
1b. Demonstrate with one of the additional MATLAB example datasets
help nndatasets
doc nndatasets
or a minor modifcation
1c. Demonstrate with your own DOWNLOADED dataset
2. Use as few modifications in the help/doc documentation code as possible.
Otherwise, help is not guaranteed.
Hope this helps.
Greg
0 commentaires
Voir également
Catégories
En savoir plus sur Deep Learning Toolbox 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!