The Evolutionary Emergence route to Artificial
Intelligence
A. Channon. School of Cognitive and Computing Sciences, University
of Sussex, UK, (1996)
Abstract
The artificial evolution of intelligence is discussed
with respect to current methods. An argument for
withdrawal of the traditional �fitness function� in
genetic algorithms is given on the grounds that this
would better enable the emergence of intelligence,
necessary because we cannot specify what intelligence
is. A modular developmental system is constructed to
aid the evolution of neural structures and a simple
virtual world with many of the properties believed
beneficial is set up to test these ideas. Resulting
emergent properties are given, along with a brief
discussion.
%0 Thesis
%1 Channon:masters
%A Channon, Alastair D.
%C UK
%D 1996
%K Artificial Development, Emergence, Fractals, Intelligence, Life, Lindenmayer Modularity, Networks, Neural Recurrence Systems, algorithms, genetic programming,
%T The Evolutionary Emergence route to Artificial
Intelligence
%U http://www.channon.net/alastair/msc/adc_msc.pdf
%X The artificial evolution of intelligence is discussed
with respect to current methods. An argument for
withdrawal of the traditional �fitness function� in
genetic algorithms is given on the grounds that this
would better enable the emergence of intelligence,
necessary because we cannot specify what intelligence
is. A modular developmental system is constructed to
aid the evolution of neural structures and a simple
virtual world with many of the properties believed
beneficial is set up to test these ideas. Resulting
emergent properties are given, along with a brief
discussion.
@mastersthesis{Channon:masters,
abstract = {The artificial evolution of intelligence is discussed
with respect to current methods. An argument for
withdrawal of the traditional �fitness function� in
genetic algorithms is given on the grounds that this
would better enable the emergence of intelligence,
necessary because we cannot specify what intelligence
is. A modular developmental system is constructed to
aid the evolution of neural structures and a simple
virtual world with many of the properties believed
beneficial is set up to test these ideas. Resulting
emergent properties are given, along with a brief
discussion.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {UK},
author = {Channon, Alastair D.},
biburl = {https://www.bibsonomy.org/bibtex/229ca4dc67134c4cd09f94eab4034153a/brazovayeye},
interhash = {e958e9ede45639a7361802ce769e1158},
intrahash = {29ca4dc67134c4cd09f94eab4034153a},
keywords = {Artificial Development, Emergence, Fractals, Intelligence, Life, Lindenmayer Modularity, Networks, Neural Recurrence Systems, algorithms, genetic programming,},
school = {School of Cognitive and Computing Sciences, University
of Sussex},
size = {30 pages},
timestamp = {2008-06-19T17:37:32.000+0200},
title = {The Evolutionary Emergence route to Artificial
Intelligence},
url = {http://www.channon.net/alastair/msc/adc_msc.pdf},
year = 1996
}