Perceptron Learning |
Introduction
This applet demonstrates a simple form of supervised learning called the
perceptron learning rule.
Using this applet, you can train the perceptron to act as a binary logic
unit. It can compute or approximate most 2-input Boolean functions. However,
a problem arises when trying to train the perceptron on the XOR (or XNOR)
function. The applet provides a "work-around" for this problem by introducing
an extra input.
Credits
The original applet was written by Fred
Corbett, and is available here.
These pages modified by Olivier Michel and Alix Herrmann.
Theory
Click on each topic to learn more. Then scroll down to the applet.
Applet
(You may need to resize your screen to see the whole applet window. )
Like the simple neuron in the first tutorial, the simple perceptron
below has just two inputs. The difference is that the learning rule
has been implemented.
Click here
to see the instructions. You may find it helpful to open a separate
browser window for the instructions, so you can view them at the same time
as the applet window.
Questions
-
Find out which patterns can be learned with the unit step activation
function. How many iterations are needed on average?
-
As above, for the sigmoid activation function.
-
As above, for the piecewise linear activation function.
-
As above, for the gaussian activation function, but first try to
guess what is going to happen. Can it learn anything at all?
-
The linear associator has no nonlinearity (identity activation function).
Can it learn the same patterns as the unit step, sigmoid, or piecewise
linear neuron? What is the role of the nonlinearity?
[Neural
Java home page]