Extracting the performance indexes / information from regression learner and neural fitting tool

1 次查看（过去 30 天）
kin ho poon
kin ho poon 2019-7-23
回答： Yogesh Khurana 2019-8-2
Hi. I am new to these two apps for building the machine learning models.
I would like to understand the performances of these models but I cannot get the complete performance indexes from both apps.
I would like to ask if there is any chance to check the MAE in % for both of the apps and RMSE by Neural Fitting tool.
Otherwise, how can I extract the results and calculate the performance indexes by my own.
Thanks.

请先登录，再回答此问题。

回答（1 个）

Yogesh Khurana
Yogesh Khurana 2019-8-2
I think it is not possible to change the performance statistics outputs of the apps:
  • Getting MSE in percentage for Regression Learner app
  • Getting RMSE for Neural Fitting app
You can get the output data from these app in our workspace and then can use it in getting the performance indexes in our way!
For exporting the data to MATLAB workspace, use Export Model option in Regression Learner app, and save it to workspace. Access various parameters of the saved model to get the fitted data and use it in calculating the desired performance indexes. For more information you can refer to the following link:
https://www.mathworks.com/help/stats/train-regression-models-in-regression-learner-app.html
For exporting data to MATLAB workspace in Neural Net Fitting tool, you can do it by training the model and then saving the output and error of the model to workspace in the form of matrix as well. After saving, you can use the data and calculate the desired performance indexes. For more information you can refer to the following link:
https://www.mathworks.com/help/deeplearning/gs/fit-data-with-a-neural-network.html

类别

在 Help Center 和 File Exchange 中查找有关 Gaussian Process Regression 的更多信息

标签

产品

Community Treasure Hunt

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

Start Hunting!

Translated by