Simple Perceptron Instructions
- First select an activation function by clicking on the
- Select a set of input-output patterns. You can then train it
automatically or one step at a time. During training, you can
watch the "decision hyperplane" evolve.
- After training, test the unit with each of the input
To Train The Perceptron:
- Select the desired Boolean function in the truth table.
- Select the desired activation function by clicking the
activation function image. You can also change some function
parameters by holding down the <Shift> key and then
clicking the image with your mouse.
- Adjust the training parameters as desired. Legal values are as
- Learning Rate: 0.0 to 1.0
- Iterations: 1 to 10000 (I wouldn't want to try
- Error Threshold: 0.0 to 0.5
- Click the Train button to begin a normal training
- Click the Step button repeatedly to single-step
through the training session.
- To stop a training session (normal or single-step) in progress,
click the Stop button.
- A few notes:
- The progress of the training session is displayed in the
progress and status bars.
- The error for the current input vector is displayed in the
Current-Error text field.
- The sum-squared error over all the input vectors is displayed
in the Sum-Squared Error text-field
- The perceptron's ability to classify the inputs into two
classes (0 and 1) is shown in a graph in the top-right corner of
the applet. Currently, this only works for the 2D
To Test The Perceptron:
- After training, click the Test button repeatedly
to cycle through all four input vectors.
- Some notes:
- If the neuron output is correct (within the error threshold
specified), the neuron output text-field is painted
otherwise it is
- The current error and sum-squared error
are updated and displayed in their text
To "Solve" the Exclusive-OR (XOR) Problem:
- Click the Show XOR Solution checkbox.
- Set the truth table to the XOR function
- Click the Train or Step button to
start a training session.
Once the training is complete, click the Test button
to check the results.
[Back to the Simple Perceptron
applet page ]