Cross-validation of single binary learners in multiclass classification (fitcecoc)

1 view (last 30 days)
Alessandro La Chioma
Alessandro La Chioma on 27 May 2017
I am training a multiclass classification model based on SVM using the function fitcecoc with coding design 'allpairs', meaning that binary models are trained for all possible combinations of class pairs.
You can cross-validate this multiclass (ECOC) classifier and estimate its generalization error by for example doing:
Mdl = fitcecoc(X,Y,'Learners',t,...
'ClassNames',{'setosa','versicolor','virginica'});
CVMdl = crossval(Mdl);
oosLoss = kfoldLoss(CVMdl)
In addition to this, would it also be possible to cross-validate and estimate the generalization error for the single binary models?

Answers (0)

Community Treasure Hunt

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

Start Hunting!