What are the influences of of the proportion 

between

    the size of the corpora (both positive & negative examples and learning and testing corpus)

    and the number of features

on the prediction qualities of various ML methods such as RF, SVM, Logistic Regression, ADABoost, and Bagging ?

Please give also explanations and relevant citations.

Thanks in advance and best regards,

Yaakov 

More Yaakov HaCohen-Kerner's questions See All
Similar questions and discussions