|
Loading a training file |
Before you can set the training parameters or train the loaded network, you must have a training file loaded.
The training file format is different for SOM to the format used in MLP and FuNN, so you need to modify the training file.
To load the training file, select Load Training File from the Train menu and browse to find the required file.
The file can have any extension, but the convention is for
training files to have the extension *.trn, and it must be
of the required format.
|
Specification of Training Parameters |
Learning rate:
A floating point number greater than or equal to zero.
If the learning rate is too high clusters will form quickly. Conversely a small learning rate will cause clusters to form more slowly.
Neighbourhood:
The area of neurons around the winning neuron that will be adjusted during the training operation.
Epochs:
The number of learning cycles during which one or more training examples are propagated through the network.
|
Viewing the training file |
You can press the View Training File button to view your training file.
Note: You need to associate files of type
*.trn with a text editor through Explorer in order to use the view
button.
|
Training in SOM |
Press the Train button to commence training, or select Train from the Train menu.
During training the bar shows the percentage of epochs that have been completed, and the number of epochs completed is shown above it.
Training is
finished when the specified number of epochs has been completed.
|
Saving the trained network |
After training is completed the network can be saved.
To do this, select Save As from the Network menu.
Give the file a name that is different from the original network file.
The file can have any extension, but the convention is for network files to have the extension *.wgt.
The only restriction is that the path cannot contain a ).