Example 3: Perceptron Learning in 2-d pattern space

The following applet further demonstrates supervised learning using the perceptron learning algorithm. Using this applet, you can train the perceptron to learn in a 2-d pattern space. By placing two distinct patterns of red dots and blue dots, the perceptron can learn to distinguish between the two.

Instructions:

To Train The Perceptron:

  1. Select the desired number of red and blue dots by clicking the radio buttons provided.
  2. Click on the white box on the left fo the applet to place red dots. To place blue dots do the same but hold down the <Shift> key.
  3. Adjust the training parameters as desired. Legal values are as follows:
  4. Click the Train button to begin a normal training session OR
  5. Click the Step button repeatedly to single-step through the training session.

During Training:

  1. To stop a training session (normal) in progress, click the Stop button.
  2. A few notes:

Some useful info:

  1. To clear the Total error list and the pattern space click Clear.
  2. To plot a graph showing the results of training click Plot.
</COMMENT>

Single Layer Single Neuron Perceptron Learning

Previous:- Example 2: The X-OR problem

Next:- MultiLayer Perceptron Learning Theory