How to save network obtained from a loop to use it for prediction?

Dear MATLAB users,

I trained my data in a loop (N=10), and I found that network{2} provides the best results. How do I save this specific network so that I can use it for prediction later with test data.

Thank you

[Manas]

please refer to this MATLAB Answer: how to save and reuse a trained neural network - MATLAB Answers - MATLAB Central (mathworks.com)

Answer 1

[VINAYAK LUHA]

Hello Nurliana,

I understand that you're training a series of neural networks within MATLAB and you wish to preserve one particular network—namely network{2}—for subsequent predictions using test data.

Here is the step by step explanation to achieve the above objective -

1.To store network{2}, you can apply the MATLAB "save" function in the following manner:

bestNetwork = network{2};
save('DestinationFolderPath\bestNetwork.mat', 'bestNetwork');

2.To retrieve the saved network back into your workspace, use the MATLAB "load" function:

load('bestNetwork.mat', 'bestNetwork');

3. For making predictions with your test data - testX , the syntax would be

testY = bestNetwork(testX');

You can refer to the following documentation for more details about the MATLAB "save" and "load" functions-

• https://www.mathworks.com/help/matlab/ref/save.html
• https://www.mathworks.com/help/matlab/ref/load.html

Hope this helps you to understand how to save and reuse trained neural network in MATLAB.

Regards,

Vinayak Luha