Understanding Particle Swarm Optimisation by Evolving Problem Landscapes W. B. Langdon Riccardo Poli, Owen Holland and Thiemo Krink (PDF) (gzip ps) to be presented at Swarm Intelligence Symposium 2005 SIG 05, Luca Maria Gambardella, Payman Arabshahi and Alcherio Martinoli (editors), 8-10 June 2005, Pasadena, California, USA.

ABSTRACT

Genetic programming (GP) is used to create fitness landscapes which highlight strengths and weaknesses of different types of PSO and to contrast population-based swarm approaches with non stochastic gradient followers (i.e.
hill climbers). These automatically generated benchmark problems yield insights into the operation of PSOs, illustrate benefits and drawbacks of different population sizes and constriction (friction) coefficients, and reveal new swarm phenomena such as deception and the exploration/exploitation tradeoff. The method could be applied to any type of optimizer.

Understanding Particle Swarm Optimisation by Evolving Problem Landscapes PDF format

Understanding Particle Swarm Optimisation by Evolving Problem Landscapes Post Script format