Unformatted text preview: distortion error elements (quantization error, neighborhood bias, and neighborhood variance) for each map unit and component sPropTotal (struct) .n = length of data .h = mean neighborhood function value .err = errors sPropMunits (struct) .Ni = hits per map unit .Hi = sum of neighborhood values for each map unit .Err = errors per map unit sPropComps (struct) .e1 = total squared distance to centroid .eq = total squared distance to BMU .Err = errors per component See also SOM_QUALITY. [ 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