ADABOOSTC

Computation of a combined classifier according to adaboost.

  [W,V,ALF] = ADABOOSTC(A,CLASSF,N,RULE,VERBOSE);

Input
A	Dataset
CLASSF	Untrained weak classifier
N	Number of classifiers to be trained, default 200
RULE	Combining rule (default: weighted voting)
VERBOSE	Suppress progress report if 0 (default)

Output
W	Combined trained classifier
V	Cell array of all classifiers  Use VC = stacked(V) for combining
ALF	Weights

Description

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

[]:	WVOTEC, weighted voting.
VOTEC	voting
MEANC	sum rule
AVERAGEC	averaging of coeffients (for linear combiners)
PRODC	product rule
MAXC	maximum rule
MINC	minimum rule
MEDIANC	median rule

Reference(s)

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

See also

mappings, datasets, prtime,