How to use the trained network to predict future values?
显示 更早的评论
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?
采纳的回答
Greg Heath
2013-10-17
0 个投票
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 个评论
Greg Heath
2013-10-23
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.
更多回答（1 个）
Jonathan LeSage
2013-10-15
0 个投票
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 个评论
MUKESH KUMAR
2020-5-6
showing error,
"Error using network/sim (line 266)
Number of inputs does not match net.numInputs."
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
