LNSC Cascade-correlation Simulator Applet
Using the Cascade-correlation algorithm, we wrote a program that
produces an output-activation diagram for a network with two continuous
input values, a single binary output unit, and random connection
weights. Here are several examples of art created by networks with
various numbers of hidden units and different color schemes.
Cascade-correlation is an algorithm for learning in neural networks
invented by Scott Fahlman of Carnegie Mellon University. In the
Laboratory for Natural and Simulated Cognition at McGill University, we
have used cascade-correlation to simulate a wide range of problems in
cognitive development. Cascade-correlation is a constructive algorithm
that creates its own topology of hidden units as it learns. For
comparison purposes, our simulator also allows the use of the popular
back-propagation algorithm, which is used with static networks that do
not change their topology.
To use either algorithm, you only need to paste in your training and
possibly test patterns and set a few parameters. Some sample pre-defined
problems are also available within the simulator.
You need the JavaT Plug-in 1.3 to view the applet below. This plug-in is
compatible with Microsoft Windows XP, Windows 2000, Windows Me, Windows
NT, or Windows 98 or 95 with the Internet Explorer or Netscape browser.
If the Java Plug-in is not already installed on your system, your
browser should be able to install it automatically. This may take a few
minutes.
If you have problem with the automatic detection and download of the
Java Plug-in 1.3, please go directly to
http://java.sun.com/products/plugin/ to download and install this
required plug-in.
Training Completion Criterion
This implementation of the cascade-correlation and back-propagation algorithms uses a
Minkowski infinity distance instead of the usual SSE (Sum of Squared Errors) as a
criterion to determine when to stop training. On a n-outputs system, the
Minkowski infinity (MINF) between the target value (x1, x2, ... xn) and the computed value
(y1, y2, ... yn), is defined as MINF = max{|x1 - y1|, |x2 - y2|, ... |xn - yn|}. When this
Minkowski infinity distance
is smaller than a pre-determined value (the score threshold parameter) for each of the training patterns,
we consider training to be successfully completed.
Cascade-Correlation Tutorial
There is an online tutorial
if you would like more details about the cascade-correlation algorithm.
Contact Information
The LNSC Cascade-correlation Simulator Applet was created by Frédéric Dandurand,
François Rivest, Martin Stolle and Tom Shultz. It is currently managed by
Peter Helfer.
For more information, or to order a copy of our lisp based simulator, please email us.