|
NeuroCOLT
Technical Report NC-TR-96-048
A
Comparison between Cellular Encoding and Direct Encoding for Genetic
Neural Networks
Frédéric
Gruau
CWI
Tthe Netherlands
Darrell
Whitley
Colorado State University
USA
Abstract
This paper compares the efficiency of two encoding schemes
for Artificial Neural Networks optimized by evolutionary algorithms.
Direct Encoding encodes the weights for an a~priori fixed neural network
architecture. Cellular Encoding encodes both weights and the architecture
of the neural network. In previous studies, Direct Encoding and Cellular
Encoding have been used to create neural networks for balancing 1
and 2 poles attached to a cart on a fixed track. The poles are balanced
by a controller that push the cart to the left or the right. In some
cases velocity information about the pole and cart is provided as
an input; in other cases the network must learn to balance a single
pole without velocity information. A careful study of the behavior
of these systems suggests that it is possible to balance a single
pole with velocity information as an input and without learning to
compute the velocity. A new fitness function is introduced that forces
ANN to compute the velocity. By using this new fitness function and
tuning the syntactic constraints used with cellular encoding, we achieve
a tenfold speedup over our previous study and solve a more difficult
problem: balancing two poles when no information about the velocity
is provided as input.
Download Compressed
Postscript
|