Thank you for taking the time to read my question.
I am trying to optimize the extraction conditions with ANN-GA. I am studying through papers and YouTube videos, but there are limits to what I can learn on my own.
How do I save a prediction model obtained through MATLAB's neural network fitting, so that I can call it in the objective function of the Optimization Toolbox?
It seems possible to save an ANN model through the "generate code/export model" menu, but when I try to call the saved file in the Optimization Toolbox.
As a MATLAB beginner, I am not familiar with operating MATLAB through commands and codes. Could you explain in a simple way how to obtain a Function that can be used in the Optimization Toolbox?
Why do you need to use the neural network model as a function in the optimization toolbox? We usually use optimization methods to train the neural network.
Sadegh Arefnezhad Thank you for your response.
I am trying to use ANN-GA for extraction method optimization like in this study: Article Optimization of Ultrasonic-Assisted Extraction Conditions fo...
.I have successfully modeled the ANN but am unsure how to convert the results from neural network fitting(nnstart) into a format (such as code or a function) that can be utilized in the optimization toolbox-ga(objective function).
You should have the trained neural network in your work space. You can use this trained model as objective function simple by using function handle. Say the name of trained model is 'trainednet'. The objective function can then be defined obj_func = predict(trainednet,x). You can use it as objective function by calling @obj_func
- Badges
- Science topic
- Similar topics
- Engineering
- Chemical Engineering