| PRTools contents |
CLASSC
V = CLASSC(W)
V = W*CLASSC
D = CLASSC(A*W)
D = A*W*CLASSC
D = CLASSC(A,W)
| Input | |
| W | Trained or untrained classifier |
| A | Dataset |
| Output | |
| V | Normalized classifier producing confidences instead of densities or distances (after training if W is untrained) |
The trained or untrained classifier W may yield densities or unnormalised confidences. The latter holds for two-class discriminants like FISHERC and SVC as well as for neural networks. Such classifiers use or should use CNORMC to convert distances to confidences. In multi-class problems as well as in combining schemes they do not produce normalises confidences. These outcomes, like the density outcomes of classifiers liek QDC, LDC and PARZENC, can be converted by CLASSC into confidences
the sum of the outcomes will be one for every object.
In case W is a one-dimensional mapping, it is converted into a two-class classifier, provided that during the construction a class label was supplied. If not, the mapping cannot be converted and an error is generated.
CLASSC lists the outcomes on the screen in case no output argument is supplied. Also true and estimated labels are supplied.
mappings, datasets, cnormc, labeld,
| PRTools contents |