F. Gruau. Adaptive Behaviour, 3 (2):
151--183(1995)
Abstract
This article illustrates an artificial developmental
system that is a computationally efficient technique
for the automatic generation of complex artificial
neural networks (ANNs). The artificial developmental
system can develop a graph grammar into a modular ANN
made of a combination of simpler subnetworks. A genetic
algorithm is used to evolve coded grammars that
generate ANNs for controlling six-legged robot
locomotion. A mechanism for the automatic definition of
neural subnetworks is incorporated. Using this
mechanism, the genetic algorithm can automatically
decompose a problem into subproblems, generate a subANN
for solving the subproblem, and instantiate copies of
this subANN to build a higher-level ANN that solves the
problem. We report some simulation results showing that
the same problem cannot be solved if the mechanism for
automatic definition of subnetworks is suppressed. We
support our argument with pictures that describe the
steps of development, how ANN structures are evolved,
and how the ANNs compute.
%0 Journal Article
%1 gruau:1995:admnn
%A Gruau, Frederic
%D 1995
%J Adaptive Behaviour
%K algorithms, animats, automatic cellular definition encoding, genetic locomotion, modularity, neural of programming, subnetworks
%N 2
%P 151--183
%T Automatic Definition of Modular Neural Networks
%U http://citeseer.ist.psu.edu/gruau95automatic.html
%V 3
%X This article illustrates an artificial developmental
system that is a computationally efficient technique
for the automatic generation of complex artificial
neural networks (ANNs). The artificial developmental
system can develop a graph grammar into a modular ANN
made of a combination of simpler subnetworks. A genetic
algorithm is used to evolve coded grammars that
generate ANNs for controlling six-legged robot
locomotion. A mechanism for the automatic definition of
neural subnetworks is incorporated. Using this
mechanism, the genetic algorithm can automatically
decompose a problem into subproblems, generate a subANN
for solving the subproblem, and instantiate copies of
this subANN to build a higher-level ANN that solves the
problem. We report some simulation results showing that
the same problem cannot be solved if the mechanism for
automatic definition of subnetworks is suppressed. We
support our argument with pictures that describe the
steps of development, how ANN structures are evolved,
and how the ANNs compute.
@article{gruau:1995:admnn,
abstract = {This article illustrates an artificial developmental
system that is a computationally efficient technique
for the automatic generation of complex artificial
neural networks (ANNs). The artificial developmental
system can develop a graph grammar into a modular ANN
made of a combination of simpler subnetworks. A genetic
algorithm is used to evolve coded grammars that
generate ANNs for controlling six-legged robot
locomotion. A mechanism for the automatic definition of
neural subnetworks is incorporated. Using this
mechanism, the genetic algorithm can automatically
decompose a problem into subproblems, generate a subANN
for solving the subproblem, and instantiate copies of
this subANN to build a higher-level ANN that solves the
problem. We report some simulation results showing that
the same problem cannot be solved if the mechanism for
automatic definition of subnetworks is suppressed. We
support our argument with pictures that describe the
steps of development, how ANN structures are evolved,
and how the ANNs compute.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Gruau, Frederic},
biburl = {https://www.bibsonomy.org/bibtex/2629927bc6d50a9dd9143fb44d82a6071/brazovayeye},
interhash = {e405427b280edaebb52e7048ba209561},
intrahash = {629927bc6d50a9dd9143fb44d82a6071},
journal = {Adaptive Behaviour},
keywords = {algorithms, animats, automatic cellular definition encoding, genetic locomotion, modularity, neural of programming, subnetworks},
notes = {ANN for controlling six legged robot locomotion,
http://www.isab.org/journal/adap3_2.php},
number = 2,
pages = {151--183},
timestamp = {2008-06-19T17:40:43.000+0200},
title = {Automatic Definition of Modular Neural Networks},
url = {http://citeseer.ist.psu.edu/gruau95automatic.html},
volume = 3,
year = 1995
}