Computation of a combined classifier according to adaboost.
[W,V,ALF] = ADABOOSTC(A,CLASSF,N,RULE,VERBOSE);
In total N weighted versions of the training set A are generated iteratevely and used for the training of the specified classifier. Weights, to be used for the probabilities of the objects in the training set to be selected, are updated according to the Adaboost rule.
The generation of base classiifers may be stopped prematurely by PRTIME.
The entire set of generated classifiers is given in V. The set of classifier weigths, according to Adaboost is returned in ALF
Various aggregating possibilities can be given in the final parameter rule
Ji Zhu, Saharon Rosset, Hui Zhou and Trevor Hastie, Multiclass Adaboost. A multiclass generalisation of the Adaboost algorithm, based on a generalisation of the exponential loss. http://www-stat.stanford.edu/~hastie/Papers/samme.pdf