Neural network tool application

1 visualización (últimos 30 días)
Gaeul Lee
Gaeul Lee el 20 de Mayo de 2015
Editada: Umakant el 20 de Mayo de 2015
When I use Neural network tool, I don't know how can I apply trained model. After I made a network file, how can I apply the model to new input data?

Respuesta aceptada

Umakant
Umakant el 20 de Mayo de 2015
Editada: Umakant el 20 de Mayo de 2015
Hi Gaeul,
As I understand you would like to test the Neural Network for new inputs(testing data). You can use the 'net' function to test the network. Please take a look at the following code snippet:
% Create a Pattern Recognition Network
hiddenLayerSize = 10;
net = patternnet(hiddenLayerSize);
% Train the Network
[net,tr] = train(net,inputs,targets);
% Test the Network
outputs = net(inputs);
errors = gsubtract(targets,outputs);
performance = perform(net,targets,outputs)
The example given above assumes a Pattern Classification Neural Network in use.If your application involves fitting data with NN please refer to the following link:
Refer to the following link for more information on Neural Network design steps:
Thanks,
Umakant

Más respuestas (0)

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