Different RMSE in Regression Learner App everytime I start a new Session

Question

Matthias Scherer 2021-7-1

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/870203-different-rmse-in-regression-learner-app-everytime-i-start-a-new-session

评论： Matthias Scherer 2021-7-2

Everytime I start a new Session in the Regression Learner App I get different RMSEs (Validation) although I am using the same model and the same dataset, features, fold numbers for k-fold. Could this occur due to k-fold partitions getting randomly initialized every time I start a new session?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Mohammad Sami 2021-7-2

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/870203-different-rmse-in-regression-learner-app-everytime-i-start-a-new-session#answer_738153

The partitions would be randomly initiated. You can set a random number seed before you begin, to try and get the same results.

https://www.mathworks.com/help/matlab/math/generate-random-numbers-that-are-repeatable.html

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Matthias Scherer 2021-7-2

And how can I use the random number seed for the regression learner app? Since I need the regression learner app to choose the best model for my data, but setting a number seed would be something I do in command window and I don`t know how to use this to affect the partitions of the k-fold cross validation in the regression learner app.

请先登录，再进行评论。