DisTools Contents

DisTools User Guide



Exact expected NN error from a dissimilarity matrix (2)

    E = NNERROR2(D,M)
    E = D*NNERROR2([],M)

 D NxN dissimilarity dataset
 M Vector with desired number of objects per class to be selected

 E Expected NN errror


Exact computation of the expected 1-nearest neighbor error. D should be a  dataset containing a labeled square dissimilarity matrix of a set of  objects related to itself. It is not needed that D is symmetric.  So NNERROR2(D) ~= NNERROR2(D') is possible.

    E = NNERROR2(D)
    E = D*NNERROR2

In this case a set of training set sizes is used to produce a full  learning curve. E can be plotted by PLOTE.

There is a similar routine NNERROR1 which is based on the random  selection of objects, instead of class-wise.

See also

datasets, nnerror1, nne, testkd,

DisTools Contents

DisTools User Guide

This file has been automatically generated. If badly readable, use the help-command in Matlab.