
Artificial Neuron
Introduction
This applet demonstrates the basic structure and behaviour of an
artificial neuron.
Credits
The original applet was written by
Fred Corbett,
and is available
here.
These pages and applet were modified by Olivier Michel, Alix
Herrmann and Gerhard Neumann.
Theory
The first computational model for an artificial neuron was
proposed by McCulloch and Pitts in 1943. The model neuron
here is similar to the McCulloch and Pitts neuron, but they are not
identical.
The general artificial neuron model has five components, shown
in the following list. (The subscript i indicates the ith input or
weight.)
 A set of
inputs,
x_{i}.
 A set of weights,
w_{i}.
 A threshold,
w_{0}.
 An
activation
function, f.
 A single
neuron output,
y.
Applet
As you can see below, an artificial neuron is a very simple
structure. This neuron has only two inputs, but in general it
could have many.
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
 Using the unit step activation function, determine a set of
weights (and threshold value) that will produce the following
classification:

x1 
x2 
output 
0.2 
0.5 
0 
0.2 
0.5 
0 
0.8 
0.8 
1 
0.8 
0.8 
1 
Try to do this by hand first, then check your answer with the
applet.
 What might the different activation functions be used
for?
