MEANC

Mean combining classifier

    W = MEANC(V)
    W = V*MEANC

Input
V	Set of classifiers (optional)

Output
W	Mean combiner

Description

If V = [V1,V2,V3, ... ] is a set of classifiers trained on the same  classes and W is the mean combiner: it selects the class with the mean of  the outputs of the input classifiers. This might also be used as  A*[V1,V2,V3]*MEANC in which A is a dataset to be classified.

If it is desired to operate on posterior probabilities then the input  classifiers should be extended like V = V*CLASSC;

For affine mappings the coefficients may be averaged instead of the  classifier results by using AVERAGEC.

The base classifiers may be combined in a stacked way (operating in the  same feature space by V = [V1,V2,V3, ... ] or in a parallel way  (operating in different feature spaces) by V = [V1;V2;V3; ... ]

Example(s)

 PREX_COMBINING

See also

mappings, datasets, votec, maxc, minc, medianc, prodc, averagec, stacked, parallel,