Trainable Feature based Dissimilarity Space Classifier
W = FDSC(A,R,FEATMAP,TYPE,P,CLASSF)
W = A*FDSC(,R,FEATMAP,TYPE,P,CLASSF)
D = X*W
| A|| Dateset used for training|
| R|| Dataset used for representation or a fraction of A to be used for this. Default: R = A.|
| FEATMAP|| Preprocessing in feature space (e.g. SCALEM) Default: no preprocessing.|
| TYPE|| Dissimilarity rule, see PROXM Default 'DISTANCE'.|
| P|| Parameter for dissimilarity rule, see PROXM Default P = 1.|
| CLASSF|| Classifier used in dissimilarity space Default LIBSVC(,,100) |
| X|| Test set|
| W|| Resulting, trained feature space classifier|
| D|| Classification matrix|
This routine builds a classifier in feature space based on a dissimilarity representation defined by the representation set R and the dissimilarities found by A*FEATMAP*PROXM(R*FEATMAP,TYPE,P). FEATMAP is a preprocessing in feature space, e.g. scaling (SCALEM(,'variance') or pre-whitening (KLMS).
R can either be explicitely given, or by a fraction of A. In the latter case the part of A that is randomly generated to create the representation set R is excluded from the training set.
New objects in feature space can be classified by D = B*W or by D = PRMAP(B,W). Labels can be found by LAB = D*LABELD or LAB = LABELD(D).
a = gendatb([100 100]); % training set of 200 objects
r = gendatb([10 10]); % representation set of 20 objects
w = fdsc(a,r); % compute classifier
scatterd(a); % scatterplot of trainingset
hold on; scatterd(r,'ko'); % add representation set to scatterplot
plotc(w); % plot classifier
datasets, mappings, scalem, klms, proxm, labeld, kernelc,
|This file has been automatically generated. If badly readable, use the help-command in Matlab.|