Weak and Strong Computational Creativity - Computational Creativity Research: Towards Creative Machines - page 39

2.3 Creativity in Swarms
2.3.1 Freedom versus Constraint
Freedom and constraint have been at the core of several definitions for creativ-
ity. Philip Johnson-Laird in his work on freedom and constraint in creativity [ 23 ]
states:
... for to be creative is to be free to choose among alternatives .. [] .. for which is not constrained
is not creative.
In swarm intelligence systems, the two phases of exploration and exploitation
introduce the freedomand control the level of constraint. Pushing the swarms towards
exploration, freedom is boosted; and by encouraging exploitation, constraint is more
emphasised. Finding a balance between exploration and exploitation has been an
important theoretical challenge in swarm intelligence research and over the years
many hundreds of different approaches have been deployed by researchers in this
field. In the presented work, two swarm intelligence algorithms are deployed: the
algorithm which is responsible for the “intelligent” tracking of the line drawing is
Particle Swarm Optimisation (PSO) [ 17 , 24 ]. This well-known algorithm, which
mimics the behaviour of birds flocking, has an internal mechanism of balancing off
the exploitation and exploration phases. However due to the weakness of the explo-
ration in this algorithm, our system also deploys another nature inspired algorithm
to overcome this weakness, Stochastic Diffusion Search (SDS) [ 1 ], which mimics
the behaviour of one species of ants ( Leptothorax acervorum ) foraging. Therefore,
exploration is promoted by utilising the SDS algorithm, whose impact on different
swarm intelligence algorithms has been scientifically reported using various mea-
sures and statistical analysis in several publications (e.g. [ 3 - 5 , 7 ]).
In the visualisation, the swarms are presented with a set of points (which constitute
a line drawing—see Fig. 2.1 ) and are set to consider these points (one at a time) as
their global optimum. In other words, the global optimum is dynamic, moving from
one position to another and the swarms aim to converge over this dynamic optimum
(Fig. 2.2 ).
As stated in the introduction, there have been several relevant attempts to create
creative computer generated artwork using Artificial Intelligence, Artificial Life and
Swarm Intelligence. Irrespective of whether the swarms are considered genuinely
creative or not, their similar individualistic approach is not totally dissimilar to those
of the “elephant artists” [ 40 ]:
After I have handed the loaded paintbrush to [the elephants], they proceed to paint in their
own distinctive style, with delicate strokes or broad ones, gently dabbing the bristles on the
paper or with a sweeping flourish, vertical lines or arcs and loops, ponderously or rapidly
and so on. No two artists have the same style.
Similarly if the same line drawing (see Fig. 2.1 ) is repeatedly given to the swarms,
the output sketches (e.g. Fig. 2.2 ) made by the swarms, are never the same (see Fig. 2.4