[Master Index] [Index for export/lyngby]



Function Synopsis

[c,C] = lyngby_classerr(T, Y, cut)

Help text

 lyngby_classerr      - Classification error

	function [c,C] = classerr(T, Y, cut)

	Input:	T	Target output
		Y	Model output
		cut	Classification threshold 
                       (optional, default = 0)

	Output:	c	Classification error in percentice
		C	Confusion matrix, O indices columns, D rows

       If T and Y has one column each it is assumed that the the
       first class is indicated by being smaller than "cut" and the
       second class is indicated by begin larger.

       If T and Y has more than one column then the largest value in
       each the column will be considered to indicate the class and
       compared to T. The values of T is assumed to be either 0 or 1.

Produced by mat2html on Wed Jul 29 15:43:40 2009
Cross-Directory links are: OFF