MATLAB Answers

How to use the trained network to predict future values?

77 views (last 30 days)
Dmitrii
Dmitrii on 15 Oct 2013
Commented: MUKESH KUMAR on 6 May 2020
Hi! I have created neural network using nnstart: NAR; d = 10. After training I saved network in workspase (name: net). Now can I use this trained network to predict future 10 values?

Accepted Answer

Greg Heath
Greg Heath on 17 Oct 2013
If the new data immediately follows the data used to design and test the net, the following syntax should have been used
[ net tr Ys Es Xsf Asf ] = train(net,Xs,Ts,Xi,Ai);
Xinew = Xsf; Ainew = Asf;
Ysnew = net(Xsnew,Xinew,Ainew);
Otherwise
Xinew = Xnew(:,1:d); Xsnew = Xnew(:,d+1:end)
but Ainew is not known.
I would try the mean of the previously used test target data rather than use zeros. Perhaps several designs using values in the interval [mean-stdv,mean+stdv] would be useful.
Hope this helps.
Thank you for formally accepting my answer
Greg
  1 Comment
Greg Heath
Greg Heath on 23 Oct 2013
This is similar to asking for the solution of a 2nd order differential equation when you know the forcing function but don't know the initial conditions.

Sign in to comment.

More Answers (1)

Jonathan LeSage
Jonathan LeSage on 15 Oct 2013
Once you have trained a network, you can use your net as a function. In your case, the outputs of the neural network could be found via outputs = net(inputs).
Here is some additional documentation that you might find helpful:
Hope this helps and best of luck!
  1 Comment
MUKESH KUMAR
MUKESH KUMAR on 6 May 2020
showing error,
"Error using network/sim (line 266)
Number of inputs does not match net.numInputs."

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!