Incorporating characteristics of human creativity into
an evolutionary art algorithm
S. DiPaola, and L. Gabora. Late breaking paper at Genetic and Evolutionary
Computation Conference (GECCO'2007), page 2450--2456. London, United Kingdom, ACM Press, (7-11 July 2007)
Abstract
A perceived limitation of evolutionary art and design
algorithms is that they rely on human intervention; the
artist selects the most aesthetically pleasing variants
of one generation to produce the next. This paper
discusses how computer generated art and design can
become more creatively human-like with respect to both
process and outcome. As an example of a step in this
direction, we present an algorithm that overcomes the
above limitation by employing an automatic fitness
function. The goal is to evolve abstract portraits of
Darwin, using our 2nd generation fitness function which
rewards genomes that not just produce a likeness of
Darwin but exhibit certain strategies characteristic of
human artists. We note that in human creativity, change
is less choosing amongst randomly generated variants
and more capitalizing on the associative structure of a
conceptual network to hone in on a vision. We discuss
how to achieve this fluidity algorithmically.
%0 Conference Paper
%1 1274009
%A DiPaola, Steve R.
%A Gabora, Liane
%B Late breaking paper at Genetic and Evolutionary
Computation Conference (GECCO'2007)
%C London, United Kingdom
%D 2007
%E Bosman, Peter A. N.
%I ACM Press
%K algorithms, art, creative creativity evolutionary genetic mechanisms of programming, systems,
%P 2450--2456
%T Incorporating characteristics of human creativity into
an evolutionary art algorithm
%U http://doi.acm.org/10.1145/1274000.1274009
%X A perceived limitation of evolutionary art and design
algorithms is that they rely on human intervention; the
artist selects the most aesthetically pleasing variants
of one generation to produce the next. This paper
discusses how computer generated art and design can
become more creatively human-like with respect to both
process and outcome. As an example of a step in this
direction, we present an algorithm that overcomes the
above limitation by employing an automatic fitness
function. The goal is to evolve abstract portraits of
Darwin, using our 2nd generation fitness function which
rewards genomes that not just produce a likeness of
Darwin but exhibit certain strategies characteristic of
human artists. We note that in human creativity, change
is less choosing amongst randomly generated variants
and more capitalizing on the associative structure of a
conceptual network to hone in on a vision. We discuss
how to achieve this fluidity algorithmically.
@inproceedings{1274009,
abstract = {A perceived limitation of evolutionary art and design
algorithms is that they rely on human intervention; the
artist selects the most aesthetically pleasing variants
of one generation to produce the next. This paper
discusses how computer generated art and design can
become more creatively human-like with respect to both
process and outcome. As an example of a step in this
direction, we present an algorithm that overcomes the
above limitation by employing an automatic fitness
function. The goal is to evolve abstract portraits of
Darwin, using our 2nd generation fitness function which
rewards genomes that not just produce a likeness of
Darwin but exhibit certain strategies characteristic of
human artists. We note that in human creativity, change
is less choosing amongst randomly generated variants
and more capitalizing on the associative structure of a
conceptual network to hone in on a vision. We discuss
how to achieve this fluidity algorithmically.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {London, United Kingdom},
author = {DiPaola, Steve R. and Gabora, Liane},
biburl = {https://www.bibsonomy.org/bibtex/21754efdecca43b3e790b08f649f1bfb1/brazovayeye},
booktitle = {Late breaking paper at Genetic and Evolutionary
Computation Conference {(GECCO'2007)}},
editor = {Bosman, Peter A. N.},
interhash = {f16b205867a1397931737360624e6b55},
intrahash = {1754efdecca43b3e790b08f649f1bfb1},
isbn13 = {978-1-59593-698-1},
keywords = {algorithms, art, creative creativity evolutionary genetic mechanisms of programming, systems,},
month = {7-11 July},
notes = {Distributed on CD-ROM at GECCO-2007 ACM Order No.
910071},
pages = {2450--2456},
publisher = {ACM Press},
publisher_address = {New York, NY, USA},
timestamp = {2008-06-19T17:38:46.000+0200},
title = {Incorporating characteristics of human creativity into
an evolutionary art algorithm},
url = {http://doi.acm.org/10.1145/1274000.1274009},
year = 2007
}