
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 2input
Boolean functions. However, a problem arises when trying to train
the perceptron on the XOR (or XNOR) function. The applet provides a
"workaround" 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?
