Landscape produced by genetic programming where Constriction helps
Particle Swarm Optimisation
Swarm of ten Particles without Constriction
10 particles without constriction factor.
In this run 116 generations were needed to find an optima.
Note as time progresses particles become increasingly energetic
and only stumble of maximum value by chance.
Swarm of ten Particles with Constriction factor of 0.7
Swarm of 10 particles operating on the same landscape as above
(note different scales)
with the same initial consitions
but
this time with a constriction factor.
Now only 11 generations are needed.
Note as time progresses particles become increasingly more focused
on the area containing the maximum value.
Example
where constriction fails.
Back to main XPS page.
W.B.Langdon
4 June 2005