How to get basic predictions out of a neural network?

2 visualizaciones (últimos 30 días)
Peta
Peta el 4 de Sept. de 2014
Respondida: Greg Heath el 7 de Sept. de 2014
I have been wondering this for days now, I’ve watched hours of Webinars and seen countless examples on neural networks. But still I don’t understand how you get it to predict a value…
If I type “nnstart” and go to Nonlinear Autoregressive and then select the “simple Nonlinear autoregressive problem” as target data and then train the network, how then do I make the prediction of value 101, 102 etc?
Or say I just have a dataseries: “1 2 3 4 5” how then do I make the neural network to give me the predictions “6 7 8…” based on its training?
What is the command that I need to write in order to get the network to simulate this for me?
It is a very trivial question that must have a simple answer, yet I have been unable to find it after days of searching. Could someone please just tell me in one simple sentence how to do this?
After all the tutorials and webinars I’ve watched I feel like I am closer to finding the cure for cancer with a neural network than I am to understanding how to get it to make predictions in a trivial data series!

Respuesta aceptada

Greg Heath
Greg Heath el 7 de Sept. de 2014
[ Ys Xf Af ] = net(Xs,Xi,Ai);
Ypred = net(cell(1,M),Xf,Af);
Hope this helps.
Thank you for formally accepting my answer
Greg

Más respuestas (0)

Categorías

Más información sobre Sequence and Numeric Feature Data Workflows en Help Center y File Exchange.

Community Treasure Hunt

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

Start Hunting!

Translated by