home *** CD-ROM | disk | FTP | other *** search
- 1. Functions of the Network Structure Estimation Program
- a. This program examines the training data and;
- b. Requests a minimum acceptable classification error
- percentage from the user. A typical number is one
- between 0 and 10.
- c. Requests a maximum number of iterations from the user.
- A typical number is 10.
- d. Estimates the required network structure for an MLP to attain
- the desired classification error percentage
- e. Notifies user if the network will generalize or memorize
-
- 2. Example Run of the Network Structure Estimation Program
- a. Go to the "Batch Processing" option and press <ret>
- b. Observe the parameter file with commented keyboard responses;
-
- GRNG ! data filename
- 16 ! number of inputs per pattern
- 3 ! minimum acceptable error percentage (0 to 10, usually)
- 8 ! maximum allowable number of iterations
-
- Here, we will estimate the required size of an MLP for
- classifying geometric shapes (elipses, triangles,
- quadrilaterals, and pentagons.
- c. Exit the DOS editor and observe the program running
- d. Go to the "Examine Program Output" option and press <ret>
- e. The program predicts that a network with 13 hidden units, in
- two hidden layers, can have a classification error percentage
- of 2.375.
- f. You can run this program on your own data, simply by editing the
- parameter file in the "batch Run" option.
-