cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
JMP is taking Discovery online, April 16 and 18. Register today and join us for interactive sessions featuring popular presentation topics, networking, and discussions with the experts.
Choose Language Hide Translation Bar
Neuroad
Level I

What are the Profile Formulas I get from the Neural Network model trained by K-fold xvalidation?

Dear community,

I trained my neural network model (Analyze => Predictive Modeling => Neural) using K-fold xvalidation, so there were K sets of model parameters generated in the training process. When I choose to Save Profile Formulas (as shown in figure below), Which set of parameters is reported to me? Is it one out of those K sets? Or some kind of average / combination of those K sets? Please advise. Thanks very much!

nn_profile_formulas.png

1 ACCEPTED SOLUTION

Accepted Solutions

Re: What are the Profile Formulas I get from the Neural Network model trained by K-fold xvalidation?

I selected the Help > Predictive and Specialized Modeling > Neural Networks > Launch the Neural Platform > Validation Method. It says:

 

"Divides the original data into K subsets. In turn, each of the K sets is used to validate the model fit on the rest of the data, fitting a total of K models. The model giving the best validation statistic is chosen as the final model."

View solution in original post

2 REPLIES 2

Re: What are the Profile Formulas I get from the Neural Network model trained by K-fold xvalidation?

I selected the Help > Predictive and Specialized Modeling > Neural Networks > Launch the Neural Platform > Validation Method. It says:

 

"Divides the original data into K subsets. In turn, each of the K sets is used to validate the model fit on the rest of the data, fitting a total of K models. The model giving the best validation statistic is chosen as the final model."

Neuroad
Level I

Re: What are the Profile Formulas I get from the Neural Network model trained by K-fold xvalidation?

Thank you so much Mark!
Felt sorry that I missed the statement when skimming over the manual very quickly...