MLP Tutorial
A. Creating the Network
- Use the following parameters to create your first MLP neural network using FuzzyCope/3:
Network Architecture:
Input Nodes |
4 |
Output Nodes |
3 |
Bias |
Check the box |
Hidden Layers |
One Layer |
Number of Nodes |
3 |
- Press the Create button
- Save the network as IrisMLP.wgt
- View the network
B. Training the network
In neural net applications the weights are determined so that they minimise the Root Mean Squared errors (RMSE).
- Open the training file that you formatted earlier - Iris.trn
- View the training file
- Set the parameters for training your Iris neural network:
Learning Rate |
0.2 |
Momentum |
0.8 |
Epochs |
500 then 1000 (increase until the terminating error is reached) |
Terminating Error |
0.01 |
LWF |
unchecked |
Training Mode |
Batch |
- Press the Train button to commence training
- Save the trained network as TIrisMLP.wgt
C. Network Evaluation
- Choose the Recall Tab
- Open your recall file that you formatted earlier - Iris.rcl
- Open a new output file for the results and name it Iris.out
- Press the Recall Button.
- View the output file.
- Compare your results with the desired outputs
D. Additional Work
Try different combinations of:
Hidden Nodes
Learning Rate
Momentum
Pattern / Batch Training Mode
This page is maintained by Melanie
Middlemiss mmiddlemiss@infoscience.otago.ac.nz
Last modified on: 4/2/99.