This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: 'size' (vector) length 2*clen-1, sizes for each of the cluster markers (scalar) this size is used for all cluster markers 'dendrogram'(vector) size 2*clen-1, indicates which clusters are shown in the dendrogram *(string) 'on' or 'off' ('on' by default) 'coord' (matrix) size dlen x odim, the coordinates for the data. If odim<=2, these are used as is. Otherwise a 2-dimensional PCA-projection is first made (see function PCAPROJ). These coordinates are applied also to the clusters. *(struct) data struct: as above map or topology struct: the coordinates given by SOM_VIS_COORDS are used for the data 'color' (matrix) size dlen x 3, color for each data. By default the colors defined for base clusters are used (sC.color(sC.base,:)). For ignored data figure background color is used. (vector) size dlen x 1, indexed colors are used See also SOM_CLSTRUCT, SOM_LINKAGE, SOM_CLPRUNE, LINKAGE, DENDROGRAM. [ SOM Toolbox online doc ]...
View Full Document
This note was uploaded on 05/23/2010 for the course CS 245 taught by Professor Dunno during the Spring '10 term at Aarhus Universitet.
- Spring '10
- Machine Learning