home *** CD-ROM | disk | FTP | other *** search
- 1. Data Pre-Processing Functions
- a. Count number of input patterns
- b. Normalize individual features, if desired
- c. Delete unwanted classes
- d. Normalize numbers of patterns per class, if desired
- e. Write new data files to disk, if desired
-
- 2. Example of Pre-Processing
- a. Go to the "Batch Processing" option and press <ret>
- b. Observe the parameter file with commented keyboard responses;
-
- 1 ! 1 for input in standard form, 2 for nonstandard
- GRNG ! data filename
- 17 ! number of numbers per pattern including inputs and class id
- 0 ! 1 to even out # patterns/class if required, 0 else
- 0 ! 1 to save data to a new file, 0 else
-
- Here, "standard form" means IANS format; inputs followed
- by the integer class id.
- c. Exit the DOS editor and observe the program running
- d. Go to the "Examine Program Output" option and press <ret>
- e. The program has counted the total number of training
- patterns or vectors and also the numbers of patterns per
- class.
- f. You can run this program on your own data. If it is not
- in IANS form, use the "Manual Run" option.