Use a trained NARX network on new input data.

2 visualizaciones (últimos 30 días)
Gustavo Santi
Gustavo Santi el 11 de Dic. de 2018
Respondida: Akshat el 12 de Nov. de 2024
Hi, I trained a NARX network and now I am trying to use the trained network on new input data to predict the result, but I can't make it work using the "net" command. Anyone has an ideia about what I have to do?

Respuestas (1)

Akshat
Akshat el 12 de Nov. de 2024
In order to make predictions using a NARX network, you need to prepare delayed inputs.
Please refer to the following official documentation link for more information:
You can use "preparets" function for preparing data with appropriate delays. Here is the documentation link for the same:
Here is a sample code snippet for your reference:
newInputData = ...;
newTargetData = []; % Use empty if you don't have target data
[Xs, Xi, Ai, Ts] = preparets(net, newInputData, {}, newTargetData);
predictedOutput = net(Xs, Xi, Ai);
% Display the predicted output
disp('Predicted Output:');
disp(predictedOutput);
Hope this helps!

Categorías

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

Etiquetas

Community Treasure Hunt

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

Start Hunting!

Translated by