I should solve binary classification task. For training (and further for new object recognition) I can use two cohorts. First have M1 records (for N1 features + label), second has M2 records (for N2 features + label), these two cohorts have N3 common features, where 0 < N3 < min(N1, N2). How to apply classification methods (SVM, Logistic Regression, etc.) for this task? Thanks a lot beforehand for your recommendations. Regards, Sergey.