A Comparison between Cellular Encoding and Direct
Encoding for Genetic Neural Networks
F. Gruau, D. Whitley, and L. Pyeatt. Genetic Programming 1996: Proceedings of the First
Annual Conference, page 81--89. Stanford University, CA, USA, MIT Press, (28--31 July 1996)
Abstract
This paper compares the efficiency of two encoding
schemes for Artificial Neural Networks optimised 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...
%0 Conference Paper
%1 gruau:1996:ceVdeGNN
%A Gruau, Frederic
%A Whitley, Darrell
%A Pyeatt, Larry
%B Genetic Programming 1996: Proceedings of the First
Annual Conference
%C Stanford University, CA, USA
%D 1996
%E Koza, John R.
%E Goldberg, David E.
%E Fogel, David B.
%E Riolo, Rick L.
%I MIT Press
%K algorithms, genetic programming
%P 81--89
%T A Comparison between Cellular Encoding and Direct
Encoding for Genetic Neural Networks
%U http://cognet.mit.edu/library/books/view?isbn=0262611279
%X This paper compares the efficiency of two encoding
schemes for Artificial Neural Networks optimised 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...
@inproceedings{gruau:1996:ceVdeGNN,
abstract = {This paper compares the efficiency of two encoding
schemes for Artificial Neural Networks optimised 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...},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Stanford University, CA, USA},
author = {Gruau, Frederic and Whitley, Darrell and Pyeatt, Larry},
biburl = {https://www.bibsonomy.org/bibtex/201ca71ababb648cf40910fb2af44b05e/brazovayeye},
booktitle = {Genetic Programming 1996: Proceedings of the First
Annual Conference},
editor = {Koza, John R. and Goldberg, David E. and Fogel, David B. and Riolo, Rick L.},
interhash = {7f3ef4b3883de7347cb48157a59a91c3},
intrahash = {01ca71ababb648cf40910fb2af44b05e},
keywords = {algorithms, genetic programming},
month = {28--31 July},
notes = {GP-96},
pages = {81--89},
publisher = {MIT Press},
size = {9 pages},
timestamp = {2008-06-19T17:40:43.000+0200},
title = {A Comparison between Cellular Encoding and Direct
Encoding for Genetic Neural Networks},
url = {http://cognet.mit.edu/library/books/view?isbn=0262611279},
year = 1996
}