a set of C++ library classes
for neural networks development



Cross validation file

File for storing cross validation results
It stores the results of cross validation. The format of the file is independent of the type of learning machine.
The file includes the following information:

The suffix of the file is .cv.

Example:
This is simple example of a results file for a 3-fold cross validation.

  
Folds number: 3
Fold n. 1
Iterations:  1813  Errors:  36   18.00%
Fold n. 2
Iterations:  1946  Errors:  43   21.50%
Fold n. 3
Iterations:  1833  Errors:  54   27.00%
Confusion matrix :
   64     0     0     0     0     0 
    4    42     0     0     0     0 
    0    18    69     0     6     1 
    0    40     1   100     0     0 
    0     0    30     0    93     0 
   32     0     0     0     1    99 

Totals:
Iterations:   5592
Errors:    133
Error rate % :  22.17 St.dev:   3.70  

Alphabetic index Hierarchy of classes


Last Updated February 2001
For comments and suggestions mail to Giorgio Valentini