Adaline, Perceptron and Backpropagation Instructions

• To specify a training set:

1. Select a category to learn, 1/red or 0/blue.
2. Click in the plane to place some points.
3. Then change the category and click to place points in the other category.
   
   
• To train the network:
  
  
1. First select a learning rule by clicking in the pop-up menu (near the top left of the applet).
2. Adjust the number of iterations and learning rate parameter in the fields near the bottom of the applet.
3. Click the Init button to initialize the network to a random set of weights.
4. Click the Learn button to train the network.  Training will run for the number of iterations (epochs) you specified; you can continue training by clicking again on Learn.
5. After training, the color of the input plane indicates the output value for that point (0.0=blue, 1.0=red).
• To compare learning rules, use the same data set each time.  When you change the learning rule, don't forget to click the Init button before training.
• Click the Clear button to erase the training set.