CMU Artificial Intelligence Repository
GACC: Genetic Aided Cascade-Correlation
areas/genetic/ga/systems/gacc/
This directory contains Genetic Aided Cascade-Correlation (GACC).
Genetic algorithms are applied to the optimization of the weights in
the cascade-correlation learning architecture. In this architecture,
the neural network starts out with a layer of output neurons. The
output neuron weights are then adjusted to minimize the error in the
network. A hidden neuron is then added and its weights adjusted so
its output correlates with the error in the network. It is then
connected to the output neurons and the weights of the output neuron
are once again readjusted. This process of adding neurons continues
until a network with an acceptable error is produced.
Genetic algorithms are used to find the weights for both the hidden
and output neurons. We attempt to use the global optimization
characteristics of genetic algorithms to find the global set of
weights. However, while simple genetic algorithms can find the area
of the weight space where there is a minimum error for the output
weights or maximum correlation for the hidden layers, they do not
converge to the actual minimum or maximum. We must find a way to
supplement the simple genetic algorithm.
In our approach, the Genetic aided cascade-correlation, we explore the
weight space first by using simple genetic algorithms with
non-overlapping populations and binary encoded weights. We then use
Quickprop to converge to the minimum or maximum. We have applied our
algorithm to the two spiral test with resulting average network sizes
of an average of 21.6 hidden nodes.
Version: 15-MAR-93
Requires: C
CD-ROM: Prime Time Freeware for AI, Issue 1-1
Author(s): Erik Mayer
Univ. of Toledo
Keywords:
Authors!Mayer, Cascade Correlation, GACC, Genetic Algorithms,
Machine Learning, Neural Networks, Quickprop,
Univ. of Toledo
References:
Mayer, E. "Genetic Aided Cascade-Correlation." COGANN Workshop ICGA-93,
Champaign-Urbana, Illinois, July, 1993.
Mayer, E. "Genetic Algorithm Approach to Neural Network Optimization."
Masters Thesis, University of Toledo, Toledo, Ohio, August 1993.
Cios, K.J., Mayer, E., Vary, A., and Kautz, H. "Neural Networks in
Analysis of Acousto-ultrasonic Data." Second International Conference
of Acousto-ultrasonics, Atlanta, Georgia, June 1993.
Last Web update on Mon Feb 13 10:22:47 1995
AI.Repository@cs.cmu.edu