Genetic synthesis of Boolean neural networks with a cell rewriting
developmental process
F. Gruau. Combinations of Genetic Algorithms and Neural Networks, 1992., COGANN-92.
International Workshop on, (6 Jun 1992)
DOI: 10.1109/COGANN.1992.273948
Abstract
Genetic algorithms (GAS) are used to generate neural networks that
implement Boolean functions. Neural networks both involve an architecture
that is a graph of connections, and a set of weights. The algorithm
that is put forward yields both the architecture and the weights
by using chromosomes that encode an algorithmic description based
upon a cell rewriting grammar. The developmental process interprets
the grammar for l cycles and develops a neural net parametrized by
l. The encoding along with the developmental process have been designed
in order to improve the existing approaches. They implement the following
key-properties. The representation on the chromosome is abstract
and compact. Any chromosome develops a valid phenotype. The developmental
process gives modular and interpretable architectures with a powerful
scalability property. The GA finds a neural net for the 50 inputs
parity function, and for the 40 inputs symmetry function
%0 Journal Article
%1 Gruau1992
%A Gruau, F.
%D 1992
%J Combinations of Genetic Algorithms and Neural Networks, 1992., COGANN-92.
International Workshop on
%K 40 50 Boolean algorithms, cell developmental encoding, function, functions, genetic grammar, grammars, inputs nets, networks, neural parity process, property rewriting scalability symmetry synthesis, systems
%P 55-74
%R 10.1109/COGANN.1992.273948
%T Genetic synthesis of Boolean neural networks with a cell rewriting
developmental process
%X Genetic algorithms (GAS) are used to generate neural networks that
implement Boolean functions. Neural networks both involve an architecture
that is a graph of connections, and a set of weights. The algorithm
that is put forward yields both the architecture and the weights
by using chromosomes that encode an algorithmic description based
upon a cell rewriting grammar. The developmental process interprets
the grammar for l cycles and develops a neural net parametrized by
l. The encoding along with the developmental process have been designed
in order to improve the existing approaches. They implement the following
key-properties. The representation on the chromosome is abstract
and compact. Any chromosome develops a valid phenotype. The developmental
process gives modular and interpretable architectures with a powerful
scalability property. The GA finds a neural net for the 50 inputs
parity function, and for the 40 inputs symmetry function
@article{Gruau1992,
abstract = {Genetic algorithms (GAS) are used to generate neural networks that
implement Boolean functions. Neural networks both involve an architecture
that is a graph of connections, and a set of weights. The algorithm
that is put forward yields both the architecture and the weights
by using chromosomes that encode an algorithmic description based
upon a cell rewriting grammar. The developmental process interprets
the grammar for l cycles and develops a neural net parametrized by
l. The encoding along with the developmental process have been designed
in order to improve the existing approaches. They implement the following
key-properties. The representation on the chromosome is abstract
and compact. Any chromosome develops a valid phenotype. The developmental
process gives modular and interpretable architectures with a powerful
scalability property. The GA finds a neural net for the 50 inputs
parity function, and for the 40 inputs symmetry function},
added-at = {2009-09-12T19:19:34.000+0200},
author = {Gruau, F.},
biburl = {https://www.bibsonomy.org/bibtex/2cc0f81480c0ce47d27085ed3855eab0f/mozaher},
doi = {10.1109/COGANN.1992.273948},
file = {:Gruau1992.pdf:PDF},
interhash = {718fe0712a8d6c6a598106e417f1dc2d},
intrahash = {cc0f81480c0ce47d27085ed3855eab0f},
journal = {Combinations of Genetic Algorithms and Neural Networks, 1992., COGANN-92.
International Workshop on},
keywords = {40 50 Boolean algorithms, cell developmental encoding, function, functions, genetic grammar, grammars, inputs nets, networks, neural parity process, property rewriting scalability symmetry synthesis, systems},
month = {6 Jun},
owner = {Mozaher},
pages = {55-74},
timestamp = {2009-09-12T19:19:39.000+0200},
title = {Genetic synthesis of Boolean neural networks with a cell rewriting
developmental process},
year = 1992
}