Prediction by using newff ?

8 views (last 30 days)
AFAQ AHMAD on 4 Jun 2015
Commented: Greg Heath on 9 Jun 2015
Hi I have the input data of 191x4 and out put of 191x1,i train my network with newff with 2 hidden layers. Now i have another input set haveing 4x4 without output,how can i get teh outputs with respect to the train neywork on the previous data. I solved this problem by using nntool,but i wnat to solve this by newff. I try sim command but it does not work. Regards Afaq Ahmad

Accepted Answer

Vinod Sudheesh
Vinod Sudheesh on 8 Jun 2015
If I understand your question correctly, you would like to know how you can compute the output when an input is applied to a trained network.
Suppose "net" is the neural network you have trained, you could compute the output for an input "X" to the neural network "net" using the following command
y = net(X);
For an example, please see the code snippet below
[X,T] = vinyl_dataset;
net = feedforwardnet(10);
net = train(net,X,T);
y = net(X);
Hope this helps !
  1 Comment
Greg Heath
Greg Heath on 9 Jun 2015
Like newff, the sim command is obsolete.
However, like newff, it still works.
y = sim(net,X);
P.S. When using neural nets, it is helpful to use lower case for double variables and reserve upper case for cell variables.

Sign in to comment.

More Answers (0)


Find more on Deep Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by