Hello, is there a possibility in MATLAB to determine the predictor scores for additional samples when I already have a PLS regression model?

1 次查看(过去 30 天)
I built a PLS Regression model a while ago and now I have new samples for which I would like to determine the predictor scores because I Need These values in order to use them as Inputs for an artificial neural Network model.

采纳的回答

Greg Heath
Greg Heath 2016-5-20
The basic tenet is
*"Can the additional data be assumed to be a random selection from the same probability
distribution as the training data?"*
Hope this helps
Greg

更多回答(1 个)

Editha Giese
Editha Giese 2016-5-20
Hello Greg, thank you very much for your answer! I would like to validate my prediction models of the artificial neural networks with these additional samples. They are from the same sample pool that I used for building the models. Editha
  1 个评论
Greg Heath
Greg Heath 2016-5-25
编辑:Greg Heath 2016-5-25
Misuse of the word validate for NN purposes. A validation set is used during training to make sure the training results in a net that can generalize well to nontraining data.
The final evaluation is obtained with a nontraining test set.
data = design + test
design = training + validation
data = training + nontraining
nontraining = validation + test
Hope this helps.
Greg

请先登录,再进行评论。

类别

Help CenterFile Exchange 中查找有关 Support Vector Machine Regression 的更多信息

Community Treasure Hunt

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

Start Hunting!

Translated by