How to perform one versus one multi class classification using LIBSVM ?

I have a data set with 15 features and 10 classes. I am not able to understand how to perform one versus one multi class classification using LIBSVM. Does it require installation of additional files (other than libsvm package). From the documentation I understood that svm-train and svm-predict are used for multi class but when I use these commands,the matlab does not recognize them. Please correct me if I have misunderstood the procedure.

Réponses (0)

Catégories

En savoir plus sur Statistics and Machine Learning Toolbox dans Centre d'aide et File Exchange

Question posée :

le 11 Mar 2015

Commenté :

A B
le 23 Sep 2016

Community Treasure Hunt

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

Start Hunting!

Translated by