SOM Tutorial
A. Creating the Network
- Use the following parameters to create your first SOM neural network using FuzzyCope/3:
Network Architecture:
Input Nodes |
4 |
Two Dimensions |
|
X |
4 |
Y |
5 |
- Press the create button.
- Save the network as IrisSOM.wgt
- View the network
B. Training the network
- Open the training file that you formatted earlier - IrisSOM.trn
- View the training file
- Set the parameters for your Iris neural network:
Learning Rate |
0.1 |
Neighbourhood |
2 2 |
Epochs |
1000 then 5000 |
- Press the Train button to commence training
- Save the trained network as TIrisSOM.wgt
C. Network Evaluation
- From the Feature Map tab press the Map button to create the map dimensions.
- Open the recall file that you formatted earlier - IrisSOM.rcl
- From the Label/Recall tab press the Recall Button.
- Save the new output file (through the Recall menu).
- View the Output file.
- Press the Label button to label the network.
- Save the label file (through the Label menu).
- Compare your results with the desired outputs.
- Go back to the Feature Map tab and plot the map.
D. Additional Work
Try different combinations of:
Map Dimensions
Learning Rate
Neighbourhood parameters
This page is maintained by Melanie Middlemiss
mmiddlemiss@infoscience.otago.ac.nz
Last modified on: 22/12/98.