Image Processing and Neural Networks Lab

Mapping Type Training and Testing Data Files

All mapping data files are in standard form. Standard form means that  the file is formatted, and that each pattern or vector has inputs on the left and desired outputs on the right. You can type out the files to examine them, and you can use these  files with other neural net software. For example, consider the  training data file, Max, part of which is shown below.

    .5844768      .5359043      .6196933     .6196933
     .1291312      .4173794      .3405759      .4173794
     .0472856      .5994965      .5638752      .5994965

Each training pattern consists of three random numbers. The fourth  number, which is the desired network output, is the maximum of the  three inputs.

 Classification Type Training and Testing Data Files

All classification data files are in standard form, which means that each pattern or feature vector is followed by the correct class number (class id). The data analysis and pre-processing  option (number 2) in our software package puts raw data into the standard format.

You can type out the data files to examine them, and you can use  these files with other neural net software. For example, consider  the training data file, Xor, shown below.

            0.  0.  1
            0.  1.  2
            1.  0.  2
            1.  1.  1

There are four training patterns with two inputs each. Patterns 1 and 4 belong to class 1, as indicated by the class number, 1, at the end of  the first and last rows. The middle two rows or training patterns belong to class 2.

Copyright © 2004 Image Processing and Neural Networks Lab
Last modified: August 21, 2009