Adaboost.M2 and probabilistic Weak Classifiers

Hello,

I'm reading each publications I found about adaboost.M2 but I have a
problem :

What need to be done whith a weak learner like Naive Bayes in order to
use it with adaboost.M2.
I already have succeeds an implementation of adaboost.M1 with a such
algorithm but I don't understand how I must modify my weak learner for
M2.

Can someone help please ?
I'm a french student, please excuse me for the approximate english.

Thanks a lot in advance.
Romain

[ comp.ai is moderated.  To submit, just post and be patient, or if ]
[ that fails mail your article to <[EMAIL PROTECTED]>, and ]
[ ask your news administrator to fix the problems with your system. ]