Computation of a combined, multi-class based mapping
W = MCLASSM(A,MAPPING,MODE,PAR)
W = A*MCLASSM(,MAPPING,MODE,PAR)
W = A*MCLASSM(MAPPING,MODE,PAR)
| A|| Dataset|
| MAPPING|| Untrained mapping|
| MODE|| Combining mode (optional; default: 'weight')|
| PAR|| Parameter needed for the combining|
| W|| Combined mapping|
If A is a unlabeled dataset or double matrix, it is converted to a one-class dataset. For one-class datasets A, the mapping is computed, calling the untrained MAPPING using the labeled samples of A only. For multi-class datasets separate mappings are determined for each class in A. They are combined as defined by MODE and PAR. The following combining rules are supported
'weight': weight the mapping outcome for class j by PAR(j) and sum over the classes. This is useful for densities in which case PAR is typically the set of class priors (these are in fact the defaults if MODE = 'weight').
| 'mean'|| combine by averaging.|
| 'min'|| combine by the minimum rule.|
| 'max'|| combine by the maximum rule.|
This routine is only defined for datasets with crisp labels.
|This file has been automatically generated. If badly readable, use the help-command in Matlab.|